Deep learning is a subfield of machine learning that employs neural networks, usually with many layers, to solve complex problems such image or speech recognition. In this example, we will look at how to leverage TensorFlow, a popular deep learning framework, using its Go bindings.
TensorFlow is a highly optimized library that was created by Google to perform calculations on objects called tensors[8]. If a vector is a collection of scalar entries (numbers) and a matrix a collection of vectors, then a tensor can be thought of as a higher-dimensional matrix, of which scalars, vectors, and matrices are special cases. While this may seem a bit abstract, tensors are natural objects to use when describing neural networks, and this is why TensorFlow has become one of the most popular libraries—even the most popular...
