Digests » 42


Learning Dynamical Systems from Partial Observations

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled by an unknown time-varying differential equation, and the evolution term is estimated from the data, using a neural network.

XKCD-style plots in Matplotlib

One of the problems I've had with typical matplotlib figures is that everything in them is so precise, so perfect.

Model-Based Reinforcement Learning for Atari

In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with orders of magnitude fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting.

A Brief History of Computer Vision (and Convolutional Neural Networks)

Computer scientists around the world have been trying to find ways to make machines extract meaning from visual data for about 60 years now, and the history of Computer Vision, which most people don’t know much about, is deeply fascinating. In this article, I’ll try to shed some light on how modern CV systems, powered primarily by convolutional neural networks, came to be.

One neural network, many uses

Build image search, image captioning, similar words and similar images using a single model.