brain of mat kelcey

a GAN experiment to generate dithers minimising pixel change between frames for a very slow movie player.

ensemble nets; using jax vmap to batch over not just the inputs of a model but also sets of multiple models parameters.

evolving a controller for cartpole using an evolutionary algorithm that operates directly on the byte level of a serialised tf lite microcontroller model.

a half baked attempt to train a pix2pix model on dash cam videos from a roadtrip around the eastern state of the u.s.

an example of using time contrastive networks to learn embeddings for the pose of a kuka arm in a pybullet simulated grasping environment.

training a fully convolutional unet to count bees from a raspberry pi stuck to the side of a hive.

one of the classic control problems of reinforcement learning is the cartpole; the oldest reference to which i can find is Barto, Sutton & Anderson's "Neuronlikw Adaptive Elements That Can Solve Difficult Learning Control Problems (1983)it's a simple...

using reinforcement learning to train neural nets for driving a simulated robot around a track.

using hadoop and a wikipedia dump to test the hypothesis that all first links on pages eventually lead to philosophy.