SynFlow: Pruning neural networks without any data by iteratively conserving synaptic flow

SynFlow: Pruning neural networks without any data by iteratively conserving synaptic flow
Share:

Download MP3


Similar Tracks

Neural Architecture Search without Training (Paper Explained) Yannic Kilcher
Deep Ensembles: A Loss Landscape Perspective (Paper Explained) Yannic Kilcher
But what are Hamming codes? The origin of error correction 3Blue1Brown
Understanding Vibration and Resonance The Efficient Engineer
Hough Transform | Boundary Detection First Principles of Computer Vision
A bio-inspired bistable recurrent cell allows for long-lasting memory (Paper Explained) Yannic Kilcher
6.3 Multiple Access links and protocols JimKurose
An introduction to Policy Gradient methods - Deep Reinforcement Learning Arxiv Insights
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures (Paper Explained) Yannic Kilcher
What Is Fuzzy Logic? | Fuzzy Logic, Part 1 MATLAB
Group Normalization (Paper Explained) Yannic Kilcher
Big Self-Supervised Models are Strong Semi-Supervised Learners (Paper Explained) Yannic Kilcher
But what is a convolution? 3Blue1Brown
Reinforcement Learning: Machine Learning Meets Control Theory Steve Brunton
Introduction to PyTorch PyTorch
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (Paper Explained) Yannic Kilcher
Harvard Professor Explains Algorithms in 5 Levels of Difficulty | WIRED WIRED
But what is a neural network? | Deep learning chapter 1 3Blue1Brown