Index

A

• abstractive summarization
  • about / Abstractive summarization
• AdaBoost algorithm
  • about / AdaBoost
  • reference link / AdaBoost
  • parameters / AdaBoost
• algorithms, baseline model
  • multinomial naive Bayes / Multinomial naive Bayes
  • C-support vector classification, with kernel rbf / C-support vector classification with kernel rbf
  • C-support vector classification, with kernel linear / C-support vector classification with kernel linear
  • linear support vector classification / Linear support vector classification
• alignment / Alignment
• Amazon review dataset
  • about / Understanding Amazon's review dataset
  • data attributes / Understanding Amazon's review dataset
• apps.tsv
  • about / apps.tsv
  • UserId / apps.tsv
  • WindowsID / apps.tsv
  • Split / apps.tsv
  • Application date / apps.tsv
  • JobID / apps.tsv
• Area Under the Curve (AUC) / AUC
• artificial intelligence (AI)
  • reference link / Keeping up to date
• Atari gaming bot
  • about / Basic Atari gaming bot
• attributes, BX-Book-Ratings.csv
  • User-ID / BX-Book-Ratings.csv
  • ISBN / BX-Book-Ratings.csv
  • Book rating / BX-Book-Ratings.csv
• attributes, BX-Books.csv
  • ISBN / BX-Books.csv
  • Book-Title / BX-Books.csv
  • Book-Author / BX-Books.csv
  • Year-Of-Publication / BX-Books.csv
  • Publisher / BX-Books.csv
  • image URL-S / BX-Books.csv
  • image URL-M / BX-Books.csv
  • image URL-L / BX-Books.csv
• attributes, BX-Users.csv
  • User-ID / BX-Users.csv
  • Location / BX-Users.csv
  • Age / BX-Users.csv
• attributes, outliers
  • revolving utilization of unsecured lines / Revolving utilization of unsecured lines
  • age / Age, Number of time 30-59 days past due not worse
  • debt ratio / Debt ratio
  • monthly income / Monthly income, Number attributes, outliersmonthly incomeof open credit lines and loans
  • data value frequency, analysis / Number of times 90 days late, Number of times 60-89 days past due not worse
  • frequency of value / Number of real estate loans or lines
  • data points, frequency value / Number of dependents

B

• bAbI dataset, chatbot development
  • about / The bAbI dataset
  • download link / The bAbI dataset
  • (20) QA bAbI tasks / The (20) QA bAbI tasks
• baseline approach
  • issues / Problems with the existing approach, Problems with the baseline approach, Problem with the existing approach
  • optimizing / Optimizing the existing approach , Optimizing the baseline approach , Optimizing the baseline approach
, How to optimize the existing approach
  • key concepts, for optimization / Understanding key concepts to optimize the approach
  • building / Building the baseline approach, Building the baseline approach
  • implementing / Implementing the baseline approach, Implementing the baseline approach, Implementing the best approach
  • data preparation / Data preparation
  • exploratory data analysis (EDA) / Exploratory data analysis (EDA)
  • customer categories, generating / Generating customer categories
  • customers classification / Classifying customers
  • customers, classification / Classifying customers
  • testing matrix / Understanding the testing matrix
  • result, testing / Testing the result of the baseline approach, Testing the result of the baseline approach
  • accuracy score, generating for classifier / Generating the accuracy score for classifier
  • confusion matrix, generating for classifier / Generating the confusion matrix for the classifier
  • learning curve, generating for classifier / Generating the learning curve for the classifier
  • basic concepts / Understanding the basic concepts
  • recommendation system, architecture / Architecture of the recommendation system
  • steps, implementing / Steps for implementing the baseline approach
  • dataset, loading / Loading the dataset, Loading the dataset
  • features generating, TF-IDF used / Generating features using TF-IDF
  • cosine similarity matrix, building / Building the cosine similarity matrix
  • prediction, generating / Generating the prediction
  • key concepts, optimizing / Understanding key concepts for optimizing the approach
  • about / The best approach
  • glove model, loading / Loading the glove model
  • preprocessing / Preprocessing
  • precomputed ID matrix, loading / Loading precomputed ID matrix
  • train and test datasets, splitting / Splitting the train and test datasets
  • neural network, building / Building a neural network
  • neural network, training / Training the neural network
  • trained model, loading / Loading the trained model
  • trained model, testing / Testing the trained model
• baseline approach, job recommendation engine
  • building / Building the baseline approach
  • implementing / Implementing the baseline approach
  • constants, defining / Defining constants
  • dataset, loading / Loading the dataset
  • helper function, defining / Defining the helper function
  • TF-IDF vectors, generating / Generating TF-IDF vectors and cosine similarity
  • testing matrix / Understanding the testing matrix
  • shortcomings / Problems with the baseline approach
  • optimizing / Optimizing the baseline approach
• baseline approach, summarization application
  • building / Building the baseline approach
  • implementing / Implementing the baseline approach
  • python dependencies, installing / Installing python dependencies
  • code, for generating summary / Writing the code and generating the summary
  • shortcomings / Problems with the baseline approach
  • optimizing / Optimizing the baseline approach
• baseline model
  • feature engineering / Feature engineering for the baseline model, Finding out Feature importance, Feature engineering for the baseline model
  • training / Training the baseline model, Training the baseline model, Training the baseline model
  • testing / Testing the baseline model, Testing the baseline model, Testing the baseline model
  • training, splitting / Splitting the training and testing dataset
  • dataset, testing / Splitting the training and testing dataset
  • prediction labels, splitting for training / Splitting prediction labels for the training and testing datasets
  • prediction labels, splitting for testing dataset / Splitting prediction labels for the training and testing datasets
  • sentiment scores, converting into numpy array / Converting sentiment scores into the numpy array
  • ML model, training / Training of the ML model
  • output, generating / Generating and interpreting the output
  • output, interpreting / Generating and interpreting the output
  • accuracy score, generating / Generating the accuracy score
  • output, visualizing / Visualizing the output
  • training and testing datasets, building / Building the training and testing datasets for the baseline model
  • implementing / Implementing the baseline model
  • multinomial naive Bayes, testing / Testing of Multinomial naive Bayes
  • SVM, testing with rbf kernel / Testing of SVM with rbf kernel
  • SVM, testing with linear kernel / Testing SVM with the linear kernel
  • SVM, testing with linearSVC / Testing SVM with linearSVC
• baseline model, Real-Time Object Recognition app
  • features engineering / Features engineering for the baseline model
  • building / Building the baseline model
  • testing / Testing the baseline model
  • shortcomings / Problem with existing approach
  • optimizing / How to optimize the existing approach
  • optimization process / Understanding the process for optimization
• basic concepts, baseline approach
  • content-based approach / Understanding the content-based approach
• basic version, chatbot development
  • about / Building the basic version of a chatbot
  • rule-based system / Why does the rule-based system work?, Understanding the rule-based system
  • implementing / Understanding the approach
  • questions, listing / Listing down possible questions and answers
  • answers, listing / Listing down possible questions and answers
  • standard messages, deciding / Deciding standard messages
  • architecture / Understanding the architecture
  • shortocmings / Problems with the existing approach
  • optimizing / Understanding key concepts for optimizing the approach
  • seq2seq model / Understanding the seq2seq model
• basic version of gaming bot
  • implementing / Implementing the basic version of the gaming bot
• best approach
  • about / The best approach
  • implementing / Implementing the best approach
• best approach, chatbot development
  • implementing / Implementing the best approach
  • random testing mode / Random testing mode
  • user interactive testing mode / User interactive testing mode
• best approach, job recommendation engine
  • about / The best approach
  • implementing / Implementing the best approach
  • dataset, filtering / Filtering the dataset
  • training dataset, preparing / Preparing the training dataset
  • concatenation operation, applying / Applying the concatenation operation
  • TF-IDF and cosine similarity score, generating / Generating the TF-IDF and cosine similarity score
  • recommendations, generating / Generating recommendations
• best approach, Real-Time Object Recognition app
  • implementing / The best approach
  • YOLO / Understanding YOLO
  • implementing, YOLO used / Implementing the best approach using YOLO
  • implementing, Darknet used / Implementation using Darknet
  • implementing, Darkflow used / Implementation using Darkflow
• best approach, summarization application
  • building / The idea behind the best approach, The best approach
  • implementing / Implementing the best approach
  • project structure / Understanding the structure of the project
  • helper functions / Understanding helper functions
  • summary, generating / Generating the summary
• Book-Crossing dataset
  • about / The Book-Crossing dataset
  • reference link / The Book-Crossing dataset
  • BX-Book-Ratings.csv / BX-Book-Ratings.csv
  • BX-Books.csv / BX-Books.csv
• BX-Book-Ratings.csv / BX-Book-Ratings.csv
• BX-Books.csv / BX-Books.csv
• BX-Users.csv / BX-Users.csv

C

• CAS-PEAL Face Dataset
  • about / CAS-PEAL Face Dataset
  • URL, for downloading / CAS-PEAL Face Dataset
• chatbot development
  • problem statement / Introducing the problem statement
  • retrieval-based approach / Retrieval-based approach
  • generative-based approach / Generative-based approach
  • open domain / Open domain
  • closed domain / Closed domain
  • short conversation / Short conversation
  • long conversation / Long conversation
  • open domain, with generative-based approach / Open domain and generative-based approach
  • open domain, with retrieval-based approach / Open domain and retrieval-based approach
  • closed domain, with retrieval-based approach / Closed domain and retrieval-based approach
  • closed domain, with generative-based approach / Closed domain and generative-based approach
  • datasets / Understanding datasets
  • basic version, building / Building the basic version of a chatbot
  • revised approach, implementing / Implementing the revised approach
  • key concepts, for solving existing problems / Understanding key concepts to solve existing problems
  • memory networks / Memory networks
  • best approach / The best approach
  • hybrid approach / Discussing the hybrid approach
• classifier model
  • generating / The best approach
  • implementing / Implementing the best approach
• closed domain chatbot
  • developing / Closed domain
• CNN-based approach
  • implementing / Implementing the CNN-based approach
• COCO dataset
  • about / The COCO dataset
  • URL / The COCO dataset
• coding environment
  • setting up / Setting up the coding environment, Setting up the coding environment
  • dlib, installing / Installing dlib
  • face recognition, installing / Installing face_recognition
• collaborative filtering
  • about / Collaborative filtering
  • memory-based CF / Memory-based CF
  • model-based CF / Model-based CF
• concepts and approaches, Logistic Regression-based approach
  • about / Understanding concepts and approaches, Logistic Regression-based approach
  • alignment-based approach / Alignment-based approach
  • smoothing-based approach / Smoothing-based approach
• confusion matrix / Confusion matrix
• consumers
  • types / Introducing customer segmentation
• context vector / Understanding the seq2seq model
• Convolutional Neural Network
  • building / Building the Convolutional Neural Network
• Convolutional Neural Network (CNN)
  • about / Convolutional Neural Network (CNN) for FR
  • Simple CNN architecture / Simple CNN architecture
  • working, for face recognition / Understanding how CNN works for FR
• Convolution Neural Network (CNN) / Why should we use a pre-trained model?
• Convolution Neural Networks (CNN ) / How to optimize the existing approach
• Cornell Movie-Dialogs dataset, chatbot development
  • about / Cornell Movie-Dialogs dataset
  • download link / Cornell Movie-Dialogs dataset
  • content of movie_conversations.txt / Content details of movie_conversations.txt
  • content of movie_lines.txt / Content details of movie_lines.txt
• correlation / Correlation
• cross-validation
  • about / Cross-validation
  • techniques / Cross-validation
  • using / The approach of using CV
  • advantages / The approach of using CV
  • disadvantages / The approach of using CV
• cross-validation based approach
  • implementing / Implementing a cross-validation based approach
• customer categories
  • generating / Generating customer categories, Generating customer categories
  • data formatting / Formatting data
  • creating / Creating customer categories
  • data encoding / Data encoding
  • PCA analysis / PCA analysis
  • cluster analyzing, silhouette scores used / Analyzing the cluster using silhouette scores
• customers classification
  • about / Classifying customers
  • helper functions, defining / Defining helper functions
  • data, splitting into training / Splitting the data into training and testing
  • data, splitting into testing / Splitting the data into training and testing
  • Machine Learning (ML) algorithm, implementing / Implementing the Machine Learning (ML) algorithm
• customer segmentation / Introducing customer segmentation
  • problem statement / Introducing the problem statement
  • references / Building the baseline approach
  • for domains / Customer segmentation for various domains
• Cython
  • installing / Installing Cython

D

• Darkflow
  • used, for YOLO implementation / Implementation using Darkflow
• Darknet
  • used, for YOLO implementation / Implementation using Darknet
• data
  • filtering, on geolocation / Filtering data based on geolocation
  • loading, dataset_loader script used / Loading the data using the dataset_loader script
• data analysis
  • about / Data analysis
  • data preprocessing / Data preprocessing, Basic data analysis followed by data preprocessing
  • statistical properties, listing / Listing statistical properties
  • missing values, finding / Finding missing values
  • missing values, replacing / Replacing missing values
  • correlation / Correlation
  • outliers detection / Detecting outliers
  • outliers, handling / Handling outliers
  / Data preprocessing and data analysis
• data attribute, NYTimes news article dataset
  • type_of_material / Understanding the NYTimes news article dataset
  • headlines / Understanding the NYTimes news article dataset
  • pub_date / Understanding the NYTimes news article dataset
  • section_name / Understanding the NYTimes news article dataset
• data attributes, exploratory data analysis (EDA)
  • country / Country
  • customer and products / Customer and products
  • customer and products / Customer and products
  • product categories / Product categories
• data formatting
  • about / Formatting data
  • products, grouping / Grouping products
  • dataset, splitting / Splitting the dataset
  • orders, grouping / Grouping orders
• data frames
  • merging / Merging the data frames
• data preparation
  • about / Data preparation
• data preprocessing
  • about / Data preprocessing
  • changes / First change, Second change
  • changes, implementing / Implementing the changes
  / Data preprocessing and data analysis
• Data science
  • reference link / Keeping up to date
• dataset
  • about / Understanding the dataset , Understanding the dataset, Understanding the datasets, Understanding the dataset
  • reference link / Understanding the dataset
  • attributes / Understanding attributes of the dataset, Attributes of the dataset
  • collecting / Collecting the dataset
  • DJIA index prices, collecting / Collecting DJIA index prices
  • news articles, collecting / Collecting news articles
  • loading / Loading the dataset, Loading the dataset, Loading the dataset
  • description / Description of the dataset
  • downloading / Downloading the dataset
  • content / Understanding the content of the dataset
  • train folder / Train folder
  • test folder / Test folder
  • imdb.vocab file / imdb.vocab file
  • imdbEr.txt file / imdbEr.txt file
  • README file / README
  • review files, content / Understanding the contents of the movie review files
  • for face emotion recognition application / Understanding the dataset for face emotion recognition
• dataset, face recognition
  • CAS-PEAL Face Dataset / CAS-PEAL Face Dataset
• dataset, Real-Time Object Recognition app
  • about / Understanding the dataset
  • COCO dataset / The COCO dataset
  • PASCAL VOC dataset / The PASCAL VOC dataset
• datasets
  • about / Understanding the datasets
  • e-commerce Item Data / e-commerce Item Data
  • Book-Crossing dataset / The Book-Crossing dataset
• datasets, chatbot development
  • about / Understanding datasets
  • Cornell Movie-Dialogs dataset / Cornell Movie-Dialogs dataset
  • bAbI dataset / The bAbI dataset
• datasets, job recommendation engine
  • about / Understanding the datasets
  • scraped dataset / Scraped dataset
  • job recommendation challenge dataset / Job recommendation challenge dataset
• datasets, summarization application
  • about / Understanding datasets
  • challenges in obtaining / Challenges in obtaining the dataset
  • medical transcription dataset / Understanding the medical transcription dataset
  • Amazon review dataset / Understanding Amazon's review dataset
• dataset training
  • reference link / Understanding the contents of the movie review files
• decoder / Understanding the seq2seq model
• Deep learning (DL) algorithms / Problem with the existing approach
• Deep Learning (DL) techniques / Understanding key concepts for optimizing the approach
• deep Q-network (DQN) / Understanding a deep Q-network (DQN)
  • architecture / Architecture of DQN
  • algorithm / Steps for the DQN algorithm
• Discounted Future Reward / Discounted Future Reward
• DJIA dataset / Understanding the DJIA dataset
  • preparing / Preparing the DJIA training dataset
  • data analysis for / Basic data analysis for a DJIA dataset
• dlib
  • installing / Installing dlib
• Dow Jones Industrial Average (DJIA) / Collecting the dataset
• Dropout
  • about / How can we use a pre-trained model?
• dynamic memory network (DMN)
  • about / Dynamic memory network (DMN)
  • architecture / Dynamic memory network (DMN)
  • semantic memory / Dynamic memory network (DMN)
  • episodic memory / Dynamic memory network (DMN), Episodic memory
  • modules / Dynamic memory network (DMN)
  • input module / Input module
  • question module / Question module

E

• e-commerce item Data
  • reference link / e-commerce Item Data
• e-commerce Item Data
  • about / e-commerce Item Data
• encoder / Understanding the seq2seq model
• existing approach
  • issues, exploring / Exploring problems with the existing approach
  • issues / Problems with the existing approach
  • optimizing / How to optimize the existing approach
  • process, optimizing / Understanding the process for optimization
• exploratory data analysis (EDA) / Basic data analysis followed by data preprocessing
  • about / Exploratory data analysis (EDA)
  • null data entries, removing / Removing null data entries
  • duplicate data entries, removing / Removing duplicate data entries
  • data attributes / EDA for various data attributes
• Exploratory Data Analysis (EDA) / Implementing the revised approach
  • about / Exploratory Data Analysis
• Exponentially Weighted Moving Average (EWMA) / Smoothing-based approach
• extractive summarization
  • about / Extractive summarization

F

• F1-score / F1-Score
• face emotion recognition application / Face emotion recognition application
  • dataset / Understanding the dataset for face emotion recognition
  • concepts / Understanding the concepts of face emotion recognition
  • convolutional layer / Understanding the convolutional layer
  • ReLU layer / Understanding the ReLU layer
  • pooling layer / Understanding the pooling layer
  • fully connected layer / Understanding the fully connected layer
  • SoftMax layer / Understanding the SoftMax layer
  • weight based on backpropagation, updating / Updating the weight based on backpropagation
• face emotion recognition model
  • building / Building the face emotion recognition model
  • data, preparing / Preparing the data
  • data, loading / Loading the data
  • model, training / Training the model
• face recognition
  • concepts / Understanding the concepts of face recognition
  • dataset / Understanding the face recognition dataset
  • Labeled Faces in Wild / Labeled Faces in the Wild
  • algorithms / Algorithms for face recognition
  • Histogram of Oriented Gradients (HOG) / Histogram of Oriented Gradients (HOG)
  • Convolutional Neural Network (CNN) / Convolutional Neural Network (CNN) for FR
  • implementing, approaches / Approaches for implementing face recognition
  • HOG-based approach, implementing / Implementing the HOG-based approach
  • CNN-based approach, implementing / Implementing the CNN-based approach
  • real-time face recognition, implementing / Implementing real-time face recognition
• face recognition application / Face recognition application
  • training / Training for the FER application
• face_recognition
  • installing / Installing face_recognition
• False Negative (FN) / Understanding the testing matrix
• False Positive (FP) / Understanding the testing matrix
• feature engineering
  • about / Feature engineering, Feature engineering
  • dataset, loading / Loading the dataset
  • minor preprocessing / Minor preprocessing
  • adj close price, converting into integer format / Converting adj close price into the integer format
  • NYTimes news articles, sentiment analysis / Sentiment analysis of NYTimes news articles
• features engineering, for baseline model
  • about / Features engineering for the baseline model
• FER2013 dataset
  • reference link / Understanding the dataset for face emotion recognition
• Flappy Bird gaming bot
  • implementing / Just for fun - implementing the Flappy Bird gaming bot

G

• gather_dataset() function
  • about / Generating question-answer pairs
• generative-based approach, chatbots
  • about / Generative-based approach
• get_conversations() function
  • about / Generating question-answer pairs
• get_id2line() function
  • about / Generating question-answer pairs
• get_summarized function
  • about / The get_summarized function
• GradientBoosting
  • about / GradientBoosting
  • parameters / GradientBoosting
• grid search parameter tuning / Grid search parameter tuning

H

• hackathons
  • strategy / Strategy for winning hackathons, Keeping up to date
• helper functions, summarization application
  • Normalization.py / Normalization.py
  • Utils.py / Utils.py
• Histogram of Oriented Gradients (HOG) / Histogram of Oriented Gradients (HOG)
• HOG-based approach
  • implementing / Implementing the HOG-based approach
• hybrid approach, chatbot development
  • about / Discussing the hybrid approach
• hyperparameter
  • tuning / Hyperparameter tuning
  • grid search parameter tuning / Grid search parameter tuning
  • random search parameter tuning / Random search parameter tuning
• hyperparameters
  • train_epochs / Implementing the best approach
  • batch_size / Implementing the best approach
  • lstm_size / Implementing the best approach
• hyperparameter tuning
  • implementing / Implementing hyperparameter tuning

I

• IMDb dataset
  • URL, for downloading / Understanding the dataset
• Intersection over Union (IoU)
  • about / Intersection over Union (IoU)
• issues, baseline approach
  • about / Problems with the baseline approach
  • limited content analysis / Problems with the baseline approach
  • over-specialization / Problems with the baseline approach
  • new-user / Problems with the baseline approach

J

• job recommendation challenge dataset
  • about / Job recommendation challenge dataset
  • apps.tsv / apps.tsv
  • users.tsv / users.tsv
  • jobs.tsv / Jobs.zip
  • user_history.tsv / user_history.tsv
• job recommendation engine
  • problem statement / Introducing the problem statement
  • datasets / Understanding the datasets
  • baseline approach, building / Building the baseline approach
  • revised approach, building / Building the revised approach
  • best approach, building / The best approach
• jobs.tsv
  • about / Jobs.zip
  • JobID / Jobs.zip
  • WindowID / Jobs.zip
  • Title / Jobs.zip
  • Description / Jobs.zip
  • Requirements / Jobs.zip
  • City / Jobs.zip
  • State / Jobs.zip
  • Country / Jobs.zip
  • Zip5 / Jobs.zip
  • StartDate / Jobs.zip
  • EndDate / Jobs.zip
• JSON attributes
  • current_form_action / Understanding the architecture
  • message_bot / Understanding the architecture
  • message_human / Understanding the architecture
  • next_field_type / Understanding the architecture
  • next_form_action / Understanding the architecture
  • placeholder_text / Understanding the architecture
  • previous_field_type / Understanding the architecture
  • previous_form_action / Understanding the architecture
  • suggestion_message / Understanding the architecture

K

• K-Nearest Neighbor (KNN)
  • about / K-Nearest Neighbor (KNN)
  • parameters / K-Nearest Neighbor (KNN)
• K-nearest neighbors (KNN) algorithm
  • about / Item-item collaborative filtering
  • reference link / Item-item collaborative filtering
  • applying / Applying the KNN algorithm
  • using / Recommendation using the KNN algorithm
• key concepts, Atari gaming bot
  • about / Understanding the key concepts
  • game rules / Rules for the game
  • Q-Learning algorithm / Understanding the Q-Learning algorithm
• key concepts, baseline approach
  • cross-validation / Cross-validation
  • hyperparameter tuning / Hyperparameter tuning
• key concepts, Pong gaming bot
  • about / Understanding the key concepts
  • architecture / Architecture of the gaming bot
  • approach / Approach for the gaming bot
• key concepts, recommendation engine
  • collaborative filtering / Collaborative filtering
  • dataset, loading / Loading the dataset
  • data frames, merging / Merging the data frames
  • EDA, for merged data frames / EDA for the merged data frames
  • data, filtering on geolocation / Filtering data based on geolocation
  • K-nearest neighbors (KNN) algorithm, applying / Applying the KNN algorithm
  • K-nearest neighbors (KNN) algorithm, using / Recommendation using the KNN algorithm
  • matrix factorization, applying / Applying matrix factorization
  • matrix factorization, using / Recommendation using matrix factorization
• key concepts, Space Invaders gaming bot
  • about / Understanding the key concepts
  • deep Q-network (DQN) / Understanding a deep Q-network (DQN)
  • Experience Replay / Understanding Experience Replay

L

• learning curve / Learning curve
• logic of correlation
  • implementing, for recommendation engine / Implementing the logic of correlation for the recommendation engine
  • rating of the books, recommendations / Recommendations based on the rating of the books
  • correlations, recommendations / Recommendations based on correlations
• Logistic regression
  • about / Logistic regression
  • parameters / Logistic regression
• log transformation of features / Log transformation of features
• Long-Short Term Memory Unit (LSTMs)
  • reference link / Building a neural network
• Long-Short Term Memory Unit (LSTMs);about / Building a neural network
• long conversation, chatbot development
  • about / Long conversation
• Long Short Term Memory (LSTM) recurrent neural networks / Understanding the seq2seq model
• loss
  • about / Loss
• LSA algorithm
  • about / The LSA algorithm
• lsa_text_summarizer function
  • about / Generating the summary
  • using / Generating the summary

M

• machine learning algorithm
  • selecting / Selecting the Machine Learning algorithm, Selecting the machine learning algorithm
• machine learning algorithm, Real-Time Object Recognition app
  • selecting / Selecting the machine learning algorithm
• machine learning algorithms
  • selecting / Selecting machine learning algorithms
  • K-Nearest Neighbor (KNN) / K-Nearest Neighbor (KNN)
  • Logistic regression / Logistic regression
  • AdaBoost algorithm / AdaBoost
  • GradientBoosting / GradientBoosting
  • RandomForest / RandomForest
• Markov Decision Process (MDP)
  • about / Markov Decision Process (MDP)
  • parameters / Markov Decision Process (MDP)
• matrix factorization
  • applying / Applying matrix factorization
  • using / Recommendation using matrix factorization
• mean Average Precision (mAP)
  • about / mean Average Precision
• medical transcription dataset
  • about / Understanding the medical transcription dataset
  • chief complaint / Understanding the medical transcription dataset
  • history of patient's illness / Understanding the medical transcription dataset
  • past medical history / Understanding the medical transcription dataset
  • past surgical history / Understanding the medical transcription dataset
  • family history / Understanding the medical transcription dataset
  • medications / Understanding the medical transcription dataset
  • physical examination / Understanding the medical transcription dataset
  • assessment / Understanding the medical transcription dataset
  • recommendations / Understanding the medical transcription dataset
  • keywords / Understanding the medical transcription dataset
• Memory-based CF
  • user-user collaborative filtering / User-user collaborative filtering
• memory-based CF
  • about / Memory-based CF
  • item-item collaborative filtering / Item-item collaborative filtering
• memory networks
  • about / Memory networks
  • dynamic memory network (DMN) / Dynamic memory network (DMN)
• merged data frames
  • EDA / EDA for the merged data frames
• methods, Term Frequency - Inverse Document Frequency (TF-IDF )
  • fit_transform() / Feature engineering for the baseline model
• minor preprocessing / Minor preprocessing
  • leftmost dot, removing from news headlines / Removing the leftmost dot from news headlines
• missing values
  • finding / Finding missing values
  • replacing / Replacing missing values
• ML algorithm / Trying a different ML algorithm
• ML model
  • testing / Testing the best approach
  • hold-out corpus, transforming in dataset training / Transforming the hold-out corpus in the form of the training dataset
  • transformed dataset, converting into matrix form / Converting the transformed dataset into a matrix form
  • precision score, generating / Generating the predictions
• ML models on real test data
  • executing / Running ML models on real test data
• MobileNet SSD
  • architecture / Architecture of the MobileNet SSD model
• model
  • testing / Testing the model
• model-based CF
  • about / Model-based CF
  • matrix-factorization-based algorithms / Matrix-factorization-based algorithms
  • versus, memory-based CF / Difference between memory-based CF and model-based CF
  • best approach, implementing / Implementing the best approach
• Multilayer Perceptron (MLP) / Why should we use a pre-trained model?
• multilayer perceptron (MLP) / The best approach

N

• Naive Bayes
  • reference link / Selecting the machine learning algorithm
• neural network-based algorithm
  • implementing / The best approach
• Normalization.py file
  • parse_document function / Normalization.py
  • remove_special_characters function / Normalization.py
  • remove_stopwords function / Normalization.py
  • unescape_html function / Normalization.py
  • pos_tag_text function / Normalization.py
  • lemmatize_text function / Normalization.py
  • expand_contractions function / Normalization.py
  • normalize_corpus function / Normalization.py
• Numberbatch's pretrained model / Preparing the dataset
• NYTimes news article dataset / Understanding the NYTimes news article dataset
• NYTimes news articles
  • sentiment analysis / Sentiment analysis of NYTimes news articles
• NYTimes news dataset
  • preparing / Preparing the NYTimes news dataset
  • publication date, converting into YYYY-MM-DD format / Converting publication date into the YYYY-MM-DD format
  • news articles, filtering by category / Filtering news articles by category
  • filter functionality, implementing / Implementing the filter functionality and merging the dataset
  • dataset, merging / Implementing the filter functionality and merging the dataset
  • merged dataset, saving in pickle file format / Saving the merged dataset in the pickle file format

O

• OpenCV
  • setting up / Setting up and installing OpenCV
  • installing / Setting up and installing OpenCV
• open domain chatbot
  • developing / Open domain
• optimization process, Real-Time Object Recognition app baseline model
  • about / Understanding the process for optimization
• outliers
  • handling / Handling outliers
• outliers detection
  • about / Detecting outliers

P

• parameter, versus hyperparameter
  • reference link / Hyperparameter tuning
• parameters, pre-trained model
  • learning rate / How can we use a pre-trained model?
  • number of epochs / How can we use a pre-trained model?
  • batch size / How can we use a pre-trained model?
  • activation function / How can we use a pre-trained model?
• parameters, Term Frequency - Inverse Document Frequency (TF-IDF )
  • min_df / Feature engineering for the baseline model
  • max_df / Feature engineering for the baseline model
  • sublinear_tf / Feature engineering for the baseline model
  • use_idf / Feature engineering for the baseline model
  • transform() / Feature engineering for the baseline model
• Part-of-Speech (POS) tags / The idea behind the best approach
• PASCAL VOC dataset
  • about / The PASCAL VOC dataset
  • PASCAL VOC classes / PASCAL VOC classes
• PDFminer
  • about / Scraped dataset
• Pearson correlation coefficient (PCC) / Recommendations based on correlations
• perplexity
  • about / Perplexity
• Pong gaming bot
  • building / Building the Pong gaming bot
  • implementing / Implementing the Pong gaming bot
  • parameters, initialization / Initialization of the parameters
  • weights, storing in form of matrices / Weights stored in the form of matrices
  • weights, updating / Updating weights
  • agent, moving / How to move the agent
  • NN, used / Understanding the process using NN
• precision / Precision
• pretrained glove model
  • reference link / Loading the glove model
• problem statement / Introducing the problem statement
• product categories
  • product description, analyzing / Analyzing the product description
  • defining / Defining product categories
  • content of clusters, characterizing / Characterizing the content of clusters
  • silhouette intra-cluster score / Silhouette intra-cluster score analysis
  • word cloud, analysis / Analysis using a word cloud
  • Principal component analysis (PCA) / Principal component analysis (PCA)
• project structure, summarization application
  • about / Understanding the structure of the project
  • Contractions.py / Understanding the structure of the project
  • Normalization.py / Understanding the structure of the project
  • Utils.py / Understanding the structure of the project
  • Document_summarization.py / Understanding the structure of the project
• PyTeaser
  • about / Installing python dependencies

R

• RandomForest
  • about / RandomForest
  • parameters / RandomForest
• random search parameter tuning / Random search parameter tuning
• real-time face recognition
  • implementing / Implementing real-time face recognition
• Real-Time Object Recognition app
  • problem statement / Introducing the problem statement
  • dataset / Understanding the dataset
  • Transfer Learning / Transfer Learning
  • coding environment, setting up / Setting up the coding environment
  • OpenCV, setting up / Setting up and installing OpenCV
  • OpenCV, installing / Setting up and installing OpenCV
  • features engineering, for baseline model / Features engineering for the baseline model
  • machine learning algorithm, selecting / Selecting the machine learning algorithm
  • MobileNet SSD architecture / Architecture of the MobileNet SSD model
  • baseline model, building / Building the baseline model
  • testing metrics / Understanding the testing metrics
  • baseline model, testing / Testing the baseline model
  • revised approach, implementing / Implementing the revised approach
  • best approach / The best approach
• recall / Recall
• Receiver Operating Characteristic (ROC) / ROC
• recommendation engine
  • about / The best approach
  • key concepts / Understanding the key concepts
• recurrent neural net (RNN) / Building a neural network
• Recurrent Neural Nets (RNN) / Understanding key concepts for optimizing the approach
• Recurrent Neural Network (RNN) / Building the DL model
• Region-based Convolution Neural Network (R-CNN) / Architecture of the MobileNet SSD model
• Reinforcement Learning (RL)
  • about / Understanding Reinforcement Learning (RL)
  • Markov Decision Process (MDP) / Markov Decision Process (MDP)
  • Discounted Future Reward / Discounted Future Reward
• reorder_sentences function
  • about / The reorder_sentences function
• retrieval-based approach, chatbots
  • about / Retrieval-based approach
• revised, baseline approach
  • implementing / Implementing the revised approach
  • dependencies, importing / Importing the dependencies
  • IMDb dataset, downloading / Downloading and loading the IMDb dataset
  • IMDb dataset, loading / Downloading and loading the IMDb dataset
  • top words, selecting / Choosing the top words and the maximum text length
  • maximum text length / Choosing the top words and the maximum text length
  • word embedding, implementing / Implementing word embedding
  • convolutional neural net (CNN), building / Building a convolutional neural net (CNN)
  • accuracy, training / Training and obtaining the accuracy
  • accuracy, obtaining / Training and obtaining the accuracy
  • testing / Testing the revised approach
  • issues / Understanding problems with the revised approach
• revised approach
  • implementing / Implementing the revised approach, Implementing and testing the revised approach , Implementing the revised approach, Implementation, Implementing the revised approach, Implementing the revised approach
  • cross-validation based approach, implementing / Implementing a cross-validation based approach
  • hyperparameter tuning, implementing / Implementing hyperparameter tuning
  • testing / Implementing and testing the revised approach , Testing the revised approach, Testing the revised approach, Testing the revised approach
  • issues / Understanding problems with the revised approach , Understanding the problem with the revised approach, Problems with the revised approach, Problems with the revised approach
  • about / Understanding the revised approach
  • alignment, implementing / Implementing alignment
  • smoothing, implementing / Implementing smoothing
  • logistic regression, implementing / Implementing logistic regression
  • building / Building the revised approach, Building the revised approach
  • improving / Understanding how to improve the revised approach, Understanding how to improve the revised approach
  • dataset, loading / Loading dataset
  • EDA of book-rating datafile / EDA of the book-rating datafile
  • book datafile, exploring / Exploring the book datafile
  • EDA of user datafile / EDA of the user datafile
  • logic of correlation, implementing for recommendation engine / Implementing the logic of correlation for the recommendation engine
• revised approach, chatbot development
  • implementing / Implementing the revised approach
  • data preparation / Data preparation
  • question-answer pairs, generating / Generating question-answer pairs
  • dataset, preprocessing / Preprocessing the dataset
  • dataset, splitting into training dataset and testing dataset / Splitting the dataset into the training dataset and the testing dataset
  • vocabulary, building for training and testing datasets / Building a vocabulary for the training and testing datasets
  • seq2seq model, building / Implementing the seq2seq model
  • model, creating / Creating the model
  • model, training / Training the model
  • testing / Testing the revised approach, Testing the revised version of the chatbot
  • testing metrics / Understanding the testing metrics
  • shortcomings / Problems with the revised approach
• revised approach, job recommendation engine
  • building / Building the revised approach
  • dataset, loading / Loading the dataset
  • training and testing datasets, splitting / Splitting the training and testing datasets
  • Exploratory Data Analysis (EDA) / Exploratory Data Analysis
  • recommendation engine, building with jobs datafile / Building the recommendation engine using the jobs datafile
  • testing / Testing the revised approach
  • shortcomings / Problems with the revised approach
  • improving / Understanding how to improve the revised approach
• revised approach, Real-Time Object Recognition app
  • implementing / Implementing the revised approach
  • testing / Testing the revised approach
  • shortcomings / Understanding problems with the revised approach
• revised approach, summarization application
  • building / Building the revised approach
  • implementing / Implementing the revised approach
  • get_summarized function / The get_summarized function
  • reorder_sentences function / The reorder_sentences function
  • summarize function / The summarize function
  • summary, generating / Generating the summary
  • shortcomings / Problems with the revised approach
  • improving / Understanding how to improve the revised approach
  • LSA algorithm / The LSA algorithm
• rule-based chatbot
  • implementing / Implementing the rule-based chatbot
  • conversation flow, implementing / Implementing the conversation flow
  • RESTful APIs, implementing with flask / Implementing RESTful APIs using flask
  • testing / Testing the rule-based chatbot
  • advantages / Advantages of the rule-based chatbot
• rule-based system
  • working / Why does the rule-based system work?
  • about / Understanding the rule-based system

S

• scraped dataset
  • about / Scraped dataset
• seq2seq model
  • about / Understanding the seq2seq model
• Sequence-to-sequence (seq2seq) neural network architecture
  • about / Generative-based approach
• short conversation, chatbot development
  • about / Short conversation
• simple TF-IDF
  • used, for building job recommendation engine / Generating TF-IDF vectors and cosine similarity
  • training dataset, building / Building the training dataset
  • IF-IDF vectors, generating for training dataset / Generating IF-IDF vectors for the training dataset
  • testing dataset, building / Building the testing dataset
  • similarity score, generating / Generating the similarity score
• Single Shot Detector (SSD) / Selecting the machine learning algorithm
• smoothing / Smoothing
• Space Invaders gaming bot
  • building / Building the Space Invaders gaming bot
  • implementing / Implementing the Space Invaders gaming bot
• standard deviation
  • reference link / Listing statistical properties
• statistical properties
  • listing / Listing statistical properties
• stocks / Introducing the problem statement
• summarization
  • basics / Understanding the basics of summarization
  • extractive summarization / Extractive summarization
  • abstractive summarization / Abstractive summarization
• summarization application
  • problem statement / Introducing the problem statement
  • datasets / Understanding datasets
  • baseline approach, building / Building the baseline approach
  • revised approach, building / Building the revised approach
  • best approach / The idea behind the best approach
• summarization application, building with Amazon reviews
  • about / Building the summarization application using Amazon reviews
  • dataset, loading / Loading the dataset
  • dataset, exploring / Exploring the dataset
  • dataset, preparing / Preparing the dataset
  • DL model, building / Building the DL model
  • DL model, training / Training the DL model
  • DL model, testing / Testing the DL model
• summarize function
  • about / The summarize function
• Sumy
  • about / Installing python dependencies
• support / Support
• Support Vector Machine (SVM) algorithm
  • about / Selecting the machine learning algorithm
  • reference link / Selecting the machine learning algorithm

T

• techniques, outliers detection
  • percentile-based outlier detection / Percentile-based outlier detection
  • Median Absolute Deviation (MAD)-based outlier detection / Median Absolute Deviation (MAD)-based outlier detection
  • Standard Deviation (STD)-based outlier detection / Standard Deviation (STD)-based outlier detection
  • Majority-vote-based outlier detection / Majority-vote-based outlier detection:
  • visualization of outliers / Visualization of outliers
• Term Frequency - Inverse Document Frequency (TF-IDF )
  • about / Feature engineering for the baseline model
• testing matrix
  • about / Understanding the testing matrix, Understanding the testing matrix, The default testing matrix, Understanding the testing matrix, Understanding the testing matrix, Understanding the testing matrix , Understanding the testing matrix
  • trained models, mean accuracy / The Mean accuracy of the trained models
  • ROC-AUC score / The ROC-AUC score
  • visualization approach / The visualization approach
  • confusion matrix / Confusion matrix
  • learning curve / Learning curve
  • precision / Precision
  • recall / Recall
  • F1-score / F1-Score
  • support / Support
  • training accuracy / Training accuracy
• testing metrics, Real-Time Object Recognition app
  • about / Understanding the testing metrics
  • Intersection over Union (IoU) / Intersection over Union (IoU)
  • mean Average Precision (mAP) / mean Average Precision
• testing metrics, revised version of chatbot
  • about / Understanding the testing metrics
  • perplexity / Perplexity
  • loss / Loss
• textrank_text_summarizer function
  • about / Generating the summary
  • using / Generating the summary
• thought vector / Understanding the seq2seq model
• trained model
  • predicting / Predicting and saving the trained model
  • saving / Predicting and saving the trained model
• Transfer Learning
  • about / Transfer Learning, What is Transfer Learning?
  • pre-trained model / What is a pre-trained model?
  • pre-trained model, advantages / What is a pre-trained model?, Why should we use a pre-trained model?
  • pre-trained model, using / How can we use a pre-trained model?
• True Negative (TN) / Understanding the testing matrix
• True Positive (TP) / Understanding the testing matrix
• Turing Test
  • reference / Open domain

U

• users.tsv
  • about / users.tsv
  • UserID / users.tsv
  • WindowID / users.tsv
  • Split / users.tsv
  • City / users.tsv
  • State / users.tsv
  • Country / users.tsv
  • ZipCode / users.tsv
  • DegreeType / users.tsv
  • Major / users.tsv
  • GraduationDate / users.tsv
  • WorkHistoryCount / users.tsv
  • TotalYearsExperience / users.tsv
  • CurrentlyEmployed / users.tsv
  • ManagedOthers / users.tsv
  • ManagedHowMany / users.tsv
• user_history.tsv
  • about / user_history.tsv
  • Sequence / user_history.tsv
  • JobTitle / user_history.tsv
• Utils.py file
  • build_feature_matrixs function / Utils.py
  • low_rank_svd function / Utils.py

V

• visualization / The visualization approach
• voting-based ensemble ML model / Voting-based ensemble ML model

Y

• YOLO
  • about / How can we use a pre-trained model?, Understanding YOLO
  • working / The working of YOLO
  • advantages / The working of YOLO
  • architecture / The architecture of YOLO
• YOLO implementation, Darkflow used
  • performing / Implementation using Darkflow
  • Cython, installing / Installing Cython
  • setup file, building / Building the already provided setup file
  • environment, testing / Testing the environment
  • object detection, running on images / Loading the model and running object detection on images
  • object detection, running on video stream / Loading the model and running object detection on the video stream
• YOLO implementation, Darknet used
  • performing / Implementation using Darknet
  • environment setup, for Darknet / Environment setup for Darknet
  • Darknet. compiling / Compiling the Darknet
  • pre-trained weight, downloading / Downloading the pre-trained weight
  • image object detection, running / Running object detection for the image