all AI news
Learning Forever, Backprop Is Insufficient
April 4, 2022, 1 p.m. | Edan Meyer
Edan Meyer www.youtube.com
Continual Learning, or Life-long learning, is becoming more popular in Machine Learning (ML). This new research paper talks about plasticity decay, and how normal backpropagation is insufficient for continual learning. The inherent non-stationary property in many problems, especially in Reinforcement Learning (RL), makes it difficult to learn. Continual Backpropagation (CBP) is proposed as a solution to this.
Outline:
0:00 - Overview
2:00 - Paper Intro
2:53 - Problems & Environments
8:11 - Plasticity Decay Experiments
11:45 - Continual …
More from www.youtube.com / Edan Meyer
I Talked with Rich Sutton
2 months, 2 weeks ago |
www.youtube.com
GPT-4 Outperforms RL by Studying and Reasoning... 🤔
7 months, 2 weeks ago |
www.youtube.com
Learning From YouTube Videos
9 months, 3 weeks ago |
www.youtube.com
RL Foundation Models Are Coming!
1 year, 1 month ago |
www.youtube.com
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Senior Data Analyst - SQL
@ Experian | Heredia, Costa Rica
Lead Business Intelligence Developer
@ L.A. Care Health Plan | Los Angeles, CA, US, 90017
(USA) Senior Manager, Data Analytics
@ Walmart | (USA) AR BENTONVILLE Home Office J Street Offices, Suite #2
Autonomous Haulage System Application Specialist
@ Komatsu | Belo Horizonte, BR
Machine Learning Engineer
@ GFT Technologies | Alcobendas, M, ES, 28108