Lecture 5: Neural Networks

Lecture 5 introduces fully-connected neural networks as a powerful nonlinear classifier. We start by discussing feature transforms plus linear classifiers as mechanism for nonlinear classification, then introduce neural networks as a mechanism for jointly learning a feature transform and a classifier. We briefly discuss differences between biological and artificial neurons. We see how fully-connected neural networks perform nonlinear classification via space warping, and discuss the universal approximation property for neural networks. We end with a brief discussion of convexity: linear classifiers give rise to convex optimization problems which are more amenable to optimization than the nonconvex optimization problems required to learn neural network classifiers.
Slides: myumi.ch/bvnX5
_________________________________________________________________________________________________
Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks.
Course Website: myumi.ch/Bo9Ng
Instructor: Justin Johnson myumi.ch/QA8Pg

[@zhaobryan4441]

truth be told, the way you teach should be the standard in this field

[@chriswang2464]

the greatest lecture for Computer vision intro of all time

[@omarespino964]

TRUE indeed! ❤

[@xiaoqingyuan8262]

beautiful

[@mohamedgamal-gi5ws]

Dr. justin is a great lecturer I came here after I finished Andrews Ng courses on coursera and I understanded a lot of concepts in a different fashion .

[@user-ok6hr3ld9h]

i love this lecture thank you prof.justin! i had a lot of trouble with studying computer vision alone before watching your lecture. this is really helpful for me.

[@hasan0770816268]

notes to self:
2:25 feature transforms to overcome shortcomings of linear classifiers
13:19 neural nets
24:40 activation function
35:13 space warping (search-space) and why use non-linearity
53:00 convex functions (training linear models optimizes convex functions)

[@jacobogerardogonzalezleon2161]

This is GOLD. Thanks Justin!

[@kelllogg]

39:45 awesome visualization of how ReLU works!! Thanks prof.Justin

[@asiimwepison]

How I wish I had this lecture 3yrs ago
Purposeful Lecture

[@iyadahmed3773]

Thank you so much for this, this is the best material to truly understanding deep learning

[@mohammadvahidi5483]

great lectures thanks

[@Davide-bx3js]

Amazing job, thanks a lot