Artificial Intelligence

Dynamic Intepretation of Random Forests Predictions

Notes on understanding why Random Forests makes its decisions. Understanding Random Forests   A good and visual explanation of how Random Forests works. Model Feature Importances Feature importances can be taken from Scikit-learn and Spark MLLib implementations after training. However, this explains features as a whole based on the training dataset. i.e. We are still …

Dynamic Intepretation of Random Forests Predictions Read More »

How Deep is your… Neural Network? How deep should it be?

How many hidden layers? How deep should your neural network be? How large or deep a fully-connected neural network can or should be? All good questions, here we explore some answers. This book’s chapter takes the cake for how large or deep a fully-connected neural network can or should be: At present day, it looks …

How Deep is your… Neural Network? How deep should it be? Read More »

Machines – More creative than humans?

Being creative or artistic has long been the sole domain of humans. What if machines are able to be as creative? What if machines get better than humans at that? Allow me to show you some contemporary developments in Artificial Intelligence that might just challenge our assumptions in these four areas: Writing Art Music Problem-solving …

Machines – More creative than humans? Read More »

Deep Blue to AlphaGo – Why Is It So Much Better?

20 years after Deep Blue defeated the World Champion at Chess, Alpha Go did the same for the World Champion at Go. What are the key changes that make it so much better? Deep Blue Excerpts from: https://en.wikipedia.org/wiki/Deep_Blue_(chess_computer) The system derived its playing strength mainly from brute force computing power. It was a massively parallel, …

Deep Blue to AlphaGo – Why Is It So Much Better? Read More »

OpenAI Lunar Lander – Solving with Vanilla DQN (aka Reinforcement Learning with Experience Replay)

In order to understand what is all the buzz about DeepMind’s reinforcement learning papers, I decided to implement Deep Reinforcement Learning with: Double Q-learning Experience Replay The neural network was then trained on the OpenAI Lunar Lander environment. I did my best to implement the above in TensorFlow with just the paper published by DeepMind …

OpenAI Lunar Lander – Solving with Vanilla DQN (aka Reinforcement Learning with Experience Replay) Read More »