Bayesian Sparsification of Deep Complex-valued networks
Jul 12, 2020
Speakers
Ivan Nazarov
Speaker · 0 followers
Evgeny Burnaev
Speaker · 0 followers
About
With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation. To this end we extend Variational Dropout to complex-valued neural networks. We verify the proposed Bayesian technique and assess the performance-compression trade-off by conducting a large-scale numerical study of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music transcription on MusicNet. We reliably replicate the state-of-the-art result by Trabelsi et al. (2017) for C-valued networks on MusicNet with 50−100x compression rate.With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation. To this end we extend Variational Dropout to complex-valued neural networks. We verify the proposed Bayesian technique and assess the performance-compression trade-off by conducting a large-scale numerical study of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music tran…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Representation Learning Using Adversarially-Contrastive Optimal Transport
Watch later
Online Continual Learning from Imbalanced Data
Watch later
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation
Watch later
Fast differentiable sorting and ranking
Watch later
Leveraging Frequency Analysis for Deep Fake Image Recognition
Watch later
Joel Frank, …
