AI News, NIPS Proceedingsβ
- On Monday, December 3, 2018
- By Read More
Part of: Advances in Neural Information Processing Systems 27 (NIPS 2014) This paper investigates how to extract objects-of-interest without relying on hand-craft features and sliding windows approaches, that aims to jointly solve two sub-tasks: (i) rapidly localizing salient objects from images, and (ii) accurately segmenting the objects based on the localizations.
We present a general joint task learning framework, in which each task (either object localization or object segmentation) is tackled via a multi-layer convolutional neural network, and the two networks work collaboratively to boost performance.
- On Tuesday, January 22, 2019
Lecture 13 | Generative Models
In Lecture 13 we move beyond supervised learning, and discuss generative modeling as a form of unsupervised learning. We cover the autoregressive PixelRNN and PixelCNN models, traditional and...
How to Train a Brain - Crash Course Psychology #11
You can directly support Crash Course at Subscribe for as little as $0 to keep up with everything we're doing. Also, if you can afford to pay a little every..
Lecture 10 | Recurrent Neural Networks
In Lecture 10 we discuss the use of recurrent neural networks for modeling sequence data. We show how recurrent neural networks can be used for language modeling and image captioning, and how...
11. The neural control of visually guided eye movements 2
MIT 9.04 Sensory Systems, Fall 2013 View the complete course: Instructor: Peter H. Schiller This video covers saccadic eye movements and the role of the superior..
Lecture 3 | GloVe: Global Vectors for Word Representation
Lecture 3 introduces the GloVe model for training word vectors. Then it extends our discussion of word vectors (interchangeably called word embeddings) by seeing how they can be evaluated intrinsic...
CMU Neural Nets for NLP 2017 (14): Neural Semantic Parsing
This lecture (by Graham Neubig) for CMU CS 11-747, Neural Networks for NLP (Fall 2017) covers: * What is Graph-based Parsing? * Minimum Spanning Tree Parsing * Structured Training and Other...
Crossing Nets Combining GANs and VAEs With Shared Latent Space Hand Pose Estimation | Spotlight 1-2B
Chengde Wan; Thomas Probst; Luc Van Gool; Angela Yao State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose modelling...
Shell PCA 1min spotlight demo at ICCV 2015
To be shown on ICCV 2015.
Correlation Doesn’t Equal Causation: Crash Course Statistics #8
Today we're going to talk about data relationships and what we can learn from them. We'll focus on correlation, which is a measure of how two variables move together, and we'll also introduce...
XLA: TensorFlow, Compiled! (TensorFlow Dev Summit 2017)
Speed is everything for effective machine learning, and XLA was developed to reduce training and inference time. In this talk, Chris Leary and Todd Wang describe how TensorFlow can make use...