⚡Interpreting Neural Networks - Avi S

Channel:
United Kingdom UWCS - University of Warwick Computing Society
Subscribers:
2,950
Published on ● Video Link: https://www.youtube.com/watch?v=uX7yRBmAj20


Duration: 11:11
263 views
9

Is it possible to reverse-engineer a trained neural network? Why might it be useful to do so? This talk gives an overview of both the advancements and challenges involved in interpreting the layers of neural networks.

Talk by Avi S



Other Videos By UWCS - University of Warwick Computing Society


2023-10-12🐍 Python Basics Sample Solutions: Variables, Datatypes, Debugging
2023-10-06X-Soc Python: Variables, Datatypes & Debugging
2023-05-23⚡ Breaking "Perfect" Security with Timing Attacks - grhkm
2023-05-07⚡ Making QR Code Art - Felix B
2023-05-02⚡ 5 Horrifying Python Techniques to get you fired - Andrew L
2023-03-24The Graduate Experience - Abhyuday R
2023-03-08Why AI Academia is Dying (and how to fix it) - Herbie B
2023-03-05Why Rust is bad, actually*
2023-03-03⚡ How Computers (try to) Keep Time - Joel C
2023-01-28Java: What They Don't Teach You
2022-12-24⚡Interpreting Neural Networks - Avi S
2022-12-21⚡ Type Level Arithmetic in Haskell - Felix B
2022-12-19⚡ Formal Concept Analysis - Josh F
2022-11-18🐍 Python Intermediate: File Handling & The Command Line
2022-11-02🦀 UWCS Learns Rust: Don't Panic!
2022-10-27⚡ Box Packing is Hard - Keegan R
2022-10-26🐍 Python Basics: Lists & Loops
2022-10-25⚡ Making Servers Gossip - Tomás F
2022-10-24🐍 Python Basics: Flow Control & Functions
2022-10-23⚡ Pokemon's Save Corruption Speedrun - Sammy Y
2022-10-22🦀 UWCS Learns Rust: Fighting the Borrow Checker


Tags:
computing
uwcs
university
society
coding
programming
neural networks
reverse-engineering
image classification
features
layers
machine learning
ai
artificial intelligence
circuits
feature detection
goal-directed
ai safety