Biologically-inspired Neural Networks for Self-Driving Cars - New Research by MITCSAIL

Oct 16, 2020

|

348 views

|

|

MITCSAIL

Recurrent Neural Networks

Details

An international research team from MIT CSAIL, TU Wien (Vienna) and IST Austria has developed a new artificial intelligence system based on the brains of tiny animals, such as threadworms. This novel AI-system can control a vehicle with only 19 artificial neurons. Read more: https://www.csail.mit.edu/news/new-deep-learning-models-require-fewer-neurons Paper URL: https://arxiv.org/abs/2006.04439

Category: Research Paper

Comments

loading...

Reactions (0) | Note

📝 No reactions yet

Be the first one to share your thoughts!

Reactions(0)

Note

loading...

Recommended

ICAPS 2014: Miquel Ramírez on "Directed Fixed-Point Regression-Based Planning..."

ICAPS | Sep 22, 2014

Representation Learning: A Review and New Perspectives

AISTATS 2014 | Nov 12, 2014

Playing Atari with Deep Reinforcement Learning | Two Minute Paper

Two Minute Papers | Mar 7, 2015

ICAPS 2014: Menkes van den Briel on "Flow-based Heuristics for Optimal Planning"

ICAPS | Mar 13, 2015

SREcon15 - Notes from Production Engineering

USENIX | Apr 9, 2015