The Lottery Ticket Hypothesis and pruning in PyTorch
In this video, we are going to explain how one can do pruning in PyTorch. We will then use this knowledge to implement a paper called “The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks“. The paper states that feedforward neural networks have subnetworks (winning tickets) inside of them that perform as good as (or even better than) the original network. It also proposes a recipe how to find them.
Paper:
Official code:
Code from this video:
00:00 Intro
00:50 Paper overview: Hypothesis (diagram) [slides]
01:33 Paper overview: Hypothesis (formal) [slides]
02:15 Paper overview: Finding winning tickets [slides]
03:44 Paper overview: Our setup [slides]
05:08 Pruning 101 in PyTorch [code]
10:29 Data - MNIST [code]
12:18 Multilayer perceptron [code]
14:05 Pruning: Linear MLP [code]
7 views
28
4
2 months ago 00:03:51 1
Jackpot! - Official Trailer | Prime Video
2 months ago 00:40:18 1
The Lottery Winners - live at Pinkpop 2024
3 months ago 00:00:19 1
We can go rizz for rizz 😏
3 months ago 01:02:50 1
EASTBOURNE. 7th TITLE. FIRE IN HOTEL. ROAD TO WIMBLEDON
3 months ago 00:00:00 1
WIN the LOTTERY ~ UNIVERSE will show YOU the WINNING NUMBERS ~ MIRACLE Activation Frequency 💲