M37.8 CONNECT THE MECHANISM
Compare learning rules, state dynamics, and hardware evidence
Hebbian rules, Hopfield nets, spikes, reservoirs, neural ODEs. Which ones quietly power today's systems, which are mostly for understanding brains, and how can you tell a real energy win from a sales pitch?
LESSON OVERVIEW14 min lesson
Lesson overview
Hebbian rules, Hopfield nets, spikes, reservoirs, neural ODEs. Which ones quietly power today's systems, which are mostly for understanding brains, and how can you tell a real energy win from a sales pitch?
What you’ll explore
- Alternative neural models should be compared by the state they update, learning signals they require, tasks they solve, and measured system costs; biological analogy and architectural novelty are separate from demonstrated advantage.
GO TO THE SOURCE
Original explanations, connected to the research.
The Hardware Lottery (Hooker, 2020)Surrogate Gradient Learning in Spiking Neural Networks (Neftci, Mostafa & Zenke, 2019)Neural Ordinary Differential EquationsNeuronal DynamicsSuggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.