Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs - Paper Explained
Start speaking a new language. It’s just 3 weeks away.
Free courses from frontend to fullstack and AI
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore a comprehensive video analysis of the paper "Predictive Coding Approximates Backprop along Arbitrary Computation Graphs." Delve into the groundbreaking research that bridges the gap between neuroscience and machine learning by demonstrating how Predictive Coding, a biologically plausible algorithm, can approximate Backpropagation for any computation graph. Learn about the experimental verification of building and training CNNs and LSTMs using Predictive Coding, and understand the implications for the similarities between brain function and deep neural networks. Follow along as the video breaks down complex concepts, provides pseudocode explanations, and offers a code walkthrough to illustrate the practical applications of this research.
Syllabus
- Intro & Overview
- Backpropagation & Biology
- Experimental Results
- Predictive Coding
- Pseudocode
- Predictive Coding approximates Backprop
- Hebbian Updates
- Code Walkthrough
- Conclusion & Comments
Taught by
Yannic Kilcher