大トロ
ml ・ design

  • archive 

Collective Intelligence for Deep Learning: A Survey of Recent Developments

October 1, 2022


We survey ideas from complex systems such as swarm intelligence, self-organization, and emergent behavior that are gaining traction in ML. (Figure: Emergence of encirclement tactics in MAgent.)


Continue reading

EvoJAX: A Hardware-Accelerated Neuroevolution

February 10, 2022



EvoJAX is a hardware-accelerated neuroevolution toolkit built on top of JAX. It can help run a wide range of evolution experiments within minutes on a TPU/GPU, compared to hours or days on CPU clusters.


Continue reading

Permutation-Invariant Neural Networks for Reinforcement Learning

November 18, 2021


Reinforcement learning agents typically perform poorly if provided with inputs that were not clearly defined in training. A new approach enables RL agents to perform well, even when subject to corrupt, incomplete, or shuffled inputs.


Continue reading

Modern Evolution Strategies for Creativity:
Fitting Concrete Images and Abstract Concepts

September 21, 2021


“A drawing of a cat”

CLIP + ES + Triangles


Continue reading

Neuroevolution of Self-Interpretable Agents

March 18, 2020


Agents with a self-attention “bottleneck” not only can solve these tasks from pixel inputs with only 4000 parameters, but they are also better at generalization.


Continue reading
Next

© otoro.net