Deep Learning Course (NYU, Spring 2020) - Week 14 – Practicum: Overfitting and regularization, and Bayesian neural nets

5.0 (0)

8 learners

What you'll learn

This course includes

42.5 hours of video
Certificate of completion
Access on mobile and TV

Summary

Keywords

Deep Learning Yann LeCun PyTorch NYU regularisation overfitting Bayesian neural networks uncertainty dropout weight decay L2 L1

Full Transcript

Course website: http://bit.ly/pDL-home Playlist: http://bit.ly/pDL-YouTube Speaker: Alfredo Canziani Week 14: http://bit.ly/pDL-en-14 0:00:00 – Week 14 – Practicum PRACTICUM: http://bit.ly/pDL-en-14-3 When training highly parametrised models such as deep neural networks there is a risk of overfitting to the training data. This leads to greater generalization error. To help reduce overfitting we can introduce regularization into our training, discouraging certain solutions to decrease the extent to which our models will fit to noise. 0:01:41 – Overfitting and regularization 0:18:11 – Model regularization (L2, L1, dropout, batch norm, and data augmentation) 0:49:30 – Visualizing Regularisation and Overfitting, Bayesian Neural Networks

Continue this lesson in the app

Install CourseHive on Android or iOS to keep learning while you move.

Related Courses

30-Day Beginner Guitar Challenge for New Players

Master the Guitar in 30 Days: Your Ultimate Beginner Challenge! Unleash your inner guitarist with step-by-step lessons designed to transform you from novice to confident player. Join Your Guitar Academy and kickstart your musical journey today!

⭐ 4.3

36 ratings

7 hours