Technical Papers

Xnor-Net

ImageNet classification using binary convolutional neural networks.

Read Full Article

YOLO 9000

We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories.

Read full article

Label Refinery

Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research.

Read full article

LCNN

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging.

Read full article

Skim-RNN

Inspired by the principles of speed reading, we introduce Skim-RNN, a recurrent neural network (RNN) that dynamically decides to update only a fraction of the hidden state for relatively unimportant input tokens.

Read full article

BiDAF

Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query.

Read full article

Re3

Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time.

Read full article
goGet started with Xnor today!
Quick Links
RetailGrocery
Technology Pages, Continued
Solar Powered AIFace RecognitionSegmentationObject Detection
Latest From Xnor
CareersBlog

© 2019 XNOR.AIPrivacy Policy