I you haven't slept under a rock for the past months you've surely heard of Google's acquisition of DeepMind, an AI company that is still quite young. For general facts about them I'll just refer you to Wikipedia or the usual news articles, but much more interestingly they've actually published quite a few papers about their methodology:
- Neural Variational Inference and Learning in Belief Networks
- Stochastic Back-Propagation and Variational Inference in Deep Latent Gaussian Models
- Deep Autoregressive Networks
- Unit Tests for Stochastic Optimization
- Deterministic Policy Gradient Algorithms
- Unsupervised Feature Learning by Deep Sparse Coding
- Playing Atari with Deep Reinforcement Learning
- Bayesian Hierarchical Community Discovery
- Learning Word Embeddings Efficiently with Noise-Contrastic Estimation
- An Approximation of the Universal Intelligence Measure
List of papers from Abram Demski
This is great news for anyone interested in Artificial Intelligence (like me) - these papers are mostly very approachable, but still provide insight into the current state of the art. Over the coming weeks, I'll read the papers listed above and write up a short discussion where interesting. I'll start of with Playing Atari with Deep Reinforcement Learning as it's the most iconic one.
Tags: ai, programming