- Deep Learning Reading Group: Skip-Thought Vectors - Nov 17, 2016.
Skip-thought vectors take inspiration from Word2Vec skip-gram and attempt to extend it to sentences, and are created using an encoder-decoder model. Read on for an overview of the paper.
- Deep Learning Reading Group: SqueezeNet - Sep 29, 2016.
This paper introduces a small CNN architecture called “SqueezeNet” that achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters.
- Deep Learning Reading Group: Deep Residual Learning for Image Recognition - Sep 22, 2016.
Published in 2015, today's paper offers a new architecture for Convolution Networks, one which has since become a staple in neural network implementation. Read all about it here.
- Deep Learning Reading Group: Deep Compression - Sep 15, 2016.
An concise overview of a paper covering three methods of compressing a neural network in order to reduce the size of the network on disk, improve performance, and decrease run time.
- Deep Learning Reading Group: Deep Networks with Stochastic Depth - Sep 8, 2016.
An concise overview of a recent paper which introduces a new way to perturb networks during training in order to improve their performance, stochastic depth networks.
- Tales from ICML: Insights and Takeaways - Aug 15, 2016.
The dust has settled from ICML 2016, having been held in June in NYC. Read some perspective on what was offered at the conference and relevant takeaways from a reflective attendee.
- 9 Must-Have Datasets for Investigating Recommender Systems - Feb 11, 2016.
Gain some insight into a variety of useful datasets for recommender systems, including data descriptions, appropriate uses, and some practical comparison.