Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.
Neural and Evolutionary Computing
EvoJAX: A Hardware-accelerated Toolkit for Neuroevolution
EvoJAX: Hardware-Accelerated Neuroevolution
Evolutionary computation has been shown to be a highly effective method for training neural networks, particularly when employed at scale on a single cluster of processors.
Recent work has also showcased their effectiveness on hardware accelerators, such as gpus, but so far such demonstrations are tailored for very specific tasks, limiting applicability to other domains.
We present evojax, a scalable, general purpose, hardware-accelerated neuroevolution toolkit.
Building on topof the jax library, our toolkit enables neuroevolution algorithms to work with neural networks running in parallel across multiple tpu/gpus.
Our toolkit achieves very high performance by implementing the evolution algorithm, neural network and task all in numpy, which is compiled just-in-time to run on accelerators.
We provide extensible examples of evojax for a wide range of tasks, including supervised learning, reinforcement learning and generative art.
We believe our toolkit can significantly shorten the iteration time of conducting experiments for researchers working with evolutionary computation.
Yujin Tang, Yingtao Tian, David Ha
Hardware-accelerated neuroevolution toolkit
Modern ML Optimizers Researchers and practitioners in the
Jack of some trades...
Testing out how it works
Read the Paper
◐ Recommended Follows
Founder 42papers.com. Also bui...
◐ Latest Activity