Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Santa Fe Institute

Training Machines to Learn the Way Humans Do - An Alternative to Backpropagation

Santa Fe Institute via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a lecture on alternative machine learning approaches that mimic human learning processes, focusing on local learning and dendrigated networks as alternatives to backpropagation. Delve into the biological basis of learning in animals, artificial neural networks, and the concept of gating inputs. Examine the cerebellum's role in learning, particularly Purkinje cells, and review computational experiments demonstrating the effectiveness of these approaches. Investigate applications in tasks such as the vestibulo-ocular reflex, predicting chaotic signals, and learning nutrition boundaries. Gain insights into the advantages of these biologically-inspired methods, including their ability to remember old tasks and train on multiple tasks simultaneously.

Syllabus

Introduction
How do animals learn
Machine learning
Artificial neural network
One layer networks
Multilayer networks
Local Learning
Dendritigated Networks
Gating
Inputs
Cat Theory
Local Learning Recap
Dendodegated Networks
Biologically Possible
Desirable Features
Cerebellum
Purkinje Cells
Experiments
Computational Experiments
Vestibulo ocular reflex
Cerebellum prediction
Learning chaotic signals
Plotting weights
Remembering old tasks
Training on multiple tasks
Hyperparameters
Example Task
Nutrition Boundaries
Learning
Directions
Conclusion
Interview

Taught by

Santa Fe Institute

Reviews

Start your review of Training Machines to Learn the Way Humans Do - An Alternative to Backpropagation

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.