Stephen Gou
YOU?
Author Swipe
View article: Intriguing Properties of Quantization at Scale
Intriguing Properties of Quantization at Scale Open
Emergent properties have been widely adopted as a term to describe behavior not present in smaller models but observed in larger models. Recent work suggests that the trade-off incurred by quantization is also an emergent property, with sh…
View article: Interlocking Backpropagation: Improving depthwise model-parallelism
Interlocking Backpropagation: Improving depthwise model-parallelism Open
The number of parameters in state of the art neural networks has drastically increased in recent years. This surge of interest in large scale neural networks has motivated the development of new distributed training strategies enabling suc…
View article: Predicting Twitter Engagement With Deep Language Models
Predicting Twitter Engagement With Deep Language Models Open
Twitter has become one of the main information sharing platforms for millions of users world-wide. Numerous tweets are created daily, many with highly time sensitive content such as breaking news, new multimedia content or personal updates…
View article: Understanding and Correcting Inaccurate Calorie Estimations on Amazon Mechanical Turk
Understanding and Correcting Inaccurate Calorie Estimations on Amazon Mechanical Turk Open
Current research on technology for fitness is often focused on tracking and encouraging healthy lifestyles. In contrast, we adopt an approach based on improving consumer knowledge of food energy. An interactive survey was distributed on Am…
View article: DQN with model-based exploration: efficient learning on environments with sparse rewards
DQN with model-based exploration: efficient learning on environments with sparse rewards Open
We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, m…