Vanishing gradient TensorFlow - accuracy scenarios

The vanishing gradient problem and ReLUs – a TensorFlow investigation

Deep learning is huge in machine learning at the moment, and no wonder – it is making large and important strides in solving problems in computer vision, natural language and reinforcement learning and problems in many other areas. Deep learning neural networks are neural networks which are characterized by many layers – making them deep instead of wide. Deep networks have been… Read More »The vanishing gradient problem and ReLUs – a TensorFlow investigation

TensorFlow Dataset tutorial - MNIST example output

TensorFlow Dataset API tutorial – build high performance data pipelines

Consuming data efficiently becomes really paramount to training performance in deep learning. In a previous post I discussed the TensorFlow data queuing framework. However, TensorFlow development is always on the move and they have now created a more streamlined and efficient way of setting up data input pipelines. This TensorFlow Dataset tutorial will show you… Read More »TensorFlow Dataset API tutorial – build high performance data pipelines

Keras LSTM tutorial architecture

Keras LSTM tutorial – How to easily build a powerful deep learning language model

In previous posts, I introduced Keras for building convolutional neural networks and performing word embedding. The next natural step is to talk about implementing recurrent neural networks in Keras. In a previous tutorial of mine, I gave a very comprehensive introduction to recurrent neural networks and long short term memory (LSTM) networks, implemented in TensorFlow.… Read More »Keras LSTM tutorial – How to easily build a powerful deep learning language model

Recurrent LSTM tutorial - unrolled RNN

Recurrent neural networks and LSTM tutorial in Python and TensorFlow

In the deep learning journey so far on this website, I’ve introduced dense neural networks and convolutional neural networks (CNNs) which explain how to perform classification tasks on static images.  We’ve seen good results, especially with CNN’s. However, what happens if we want to analyze dynamic data? What about videos, voice recognition or sequences of text?… Read More »Recurrent neural networks and LSTM tutorial in Python and TensorFlow

gensim Word2Vec - nearest words

Python gensim Word2Vec tutorial with TensorFlow and Keras

I’ve been dedicating quite a bit of time recently to Word2Vec tutorials because of the importance of the Word2Vec concept for natural language processing (NLP) and also because I’ll soon be presenting some tutorials on recurrent neural networks and LSTMs for sequence prediction/NLP (UPDATE: I’ve completed a comprehensive tutorial on these topics – Recurrent neural… Read More »Python gensim Word2Vec tutorial with TensorFlow and Keras