Neural network implementation guidelines

Today to conclude my series on neural network I am going to write down some guidelines and methodology for developing, testing and debugging a neural network. As we will see (or as you already experienced) implementing a neural network is tricky and there is often a thin line between failure and success – between something […]

Recurrent Neural Network

After introducing the convolutional neural networks I continue my serie on neural networks with another kind of specialised network: the recurrent neural network. Principle The recurrent neural network is a kind of neural network that specialises in sequential input data. With traditional neural network sequential data (e.g. time series) are split into fixed-sized windows and only the data […]

Convolutional Neural Network

Inspiration Convolutional Neural Networks are a kind of network inspired by the cats’ visual cortex. A cat visual cortex is made of 2 distinct type of cells: simple cells which specializes into edge detection. complex cells with larger receptive field which are sensitive to a small region of the visual field and are less sensitive to the exact […]

Keras – Tensorflow and Theano abstraction

As we’ve seen in the Tensorflow introduction having access to the computation  is a powerful feature. We can define any operation we’d like and tensor flow (or Theano) will compute the gradient and perform the optimisation for us. That’s great! However if you always define the same kind of operation you’ll eventually find this approach a […]

Neural Network

Machine learning applications widespread every day in many domains. One of today’s most powerful techniques is the neural network. This technique is employed in many applications such as image recognition, speech analysis and translation, self-driving cars, etc… In fact such learning algorithms have been known for decades. But only recently it has become mainstream supported by […]