Dueling Network Architectures for Deep Reinforcement Learning

"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or…Read More

AdaGAN: Boosting Generative Models

Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to train and can suffer…Read More

Robots that Learn

"The system is powered by two neural networks: a vision network and an imitation network.

The vision network ingests an image from the robot’s camera and outputs state representing the positions of the…Read More

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is a first step in this direction.…Read More

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they're like optical illusions for machines. In this post we'll show…Read More

The realities of machine learning systems - SD Times

"Machine learning is today’s Industrial Revolution. TV shows and movies currently portray machine learning as this creepy, self-aware, futuristic technology that takes over humans’ jobs, but these examples…Read More