What deep learning cannot do

After the AI winter of the 70s, the combination of data and hardware improvements have changed the way researchers tackle the hard computing problems of the century. It seems however...

Read more

Parallelizing and distributing Stochastic Gradient Descent

Continuing the discussion of the last two episodes, there is one more aspect of deep learning that I would love to consider and therefore left as a full episode, that is parallelising and distributing deep learning on relatively large clusters.

Read more

Additional optimisation strategies for deep learning

In this episode I would like to continue that conversation about some additional strategies for optimising gradient descent in deep learning and explain some tricks that might come useful when your neural network stops learning

Read more

How to master optimisation in deep learning

The secret behind deep learning is not really a secret. It is *function optimisation*. What a neural network does, is optimising a function. For instance, let’s take the image classifier example...

Read more

Completely change your data analytics strategy with deep learning

I am recording this episode from South Africa, exactly in Cape Town, as we are currently participating to the Barclays accelerator powered by Techstars, putting our AI expertise to the test in the complex financial environments of corporations like Barclays and their affiliates.

Read more

Machines that learn like humans

Podcast episode with Google software engineer Brett Zhiyuan

In the era of Artificial Intelligence and Deep Learning, we are dealing with machines that learn...well... like machines. I had a very interesting conversation with Brett Zhiyuan Chen, software engineer at Google

Read more