YoVDO

Democratizing Deep Learning with DeepHyper

Offered By: Scalable Parallel Computing Lab, SPCL @ ETH Zurich via YouTube

Tags

Deep Learning Courses Machine Learning Courses Ensemble Learning Courses Hyperparameter Optimization Courses Scientific Computing Courses Automated Machine Learning Courses Neural Architecture Search Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore an in-depth lecture on democratizing deep learning through DeepHyper, presented by Prasanna Balaprakash at the SPCL_Bcast event. Delve into the challenges of designing high-performing deep neural network (DNN) architectures for diverse scientific datasets and discover how DeepHyper, a software package, automates this process using scalable neural architecture and hyperparameter search. Learn about recent advancements in generating DNN ensembles at scale and their application in estimating data and model uncertainties across various scientific domains. Gain insights into the potential of DeepHyper to revolutionize DNN model development for scientific and engineering applications, making deep learning more accessible and efficient.

Syllabus

Intro
Talk
Announcements
Q&A


Taught by

Scalable Parallel Computing Lab, SPCL @ ETH Zurich

Related Courses

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
DeepLearning.AI via Coursera How to Win a Data Science Competition: Learn from Top Kagglers
Higher School of Economics via Coursera Predictive Modeling and Machine Learning with MATLAB
MathWorks via Coursera Machine Learning Rapid Prototyping with IBM Watson Studio
IBM via Coursera Hyperparameter Tuning with Neural Network Intelligence
Coursera Project Network via Coursera