Lecture 12: Recurrent Networks

Lecture 12 introduces recurrent neural networks (RNNs) as a new type of neural network that processes sequential data. We see how they can be used to solve new types of problems involving sequences, including many-to-one, one-to-many, and sequence-to-sequence problems. We discuss language modeling, and see how truncated backpropagation through time allows training RNNs on very long sequences. We see how recurrent networks allow us to solve new computer vision problems such as image captioning. We see how gradient flow is a crucial issue when training recurrent networks, and how Long Short Term Memory (LSTM) RNNs help avoid vanishing and exploding gradients.

Slides: http://myumi.ch/Bo9jg
_________________________________________________________________________________________________

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: http://myumi.ch/Bo9Ng

Instructor: Justin Johnson http://myumi.ch/QA8Pg

Видео Lecture 12: Recurrent Networks канала Michigan Online