Offsite Link

DSOD: Deeply Supervised Object Detectors

This research paper introduces DSOD, a framework that outperforms modern variations of regional proposal and classification networks.

Authored by admin Last updated on 08/02/2018 - 10:41
Offsite Link

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

This research shows how training low-bit deep neural networks has a much smaller memory footprint than full-precision models but with a small cost to accuracy.

Authored by admin Last updated on 08/02/2018 - 10:42
Offsite Link

Fast Weight Long Short-Term Memory

Read about a mechanism to improve the memory capacity and time-scale of recurrent neural networks that allows for higher accuracy and faster training.

Authored by admin Last updated on 08/02/2018 - 10:42
Offsite Link

Fruit Quantity and Quality Estimation Using a Robotic Vision System

This robotic vision innovation uses Intel® RealSense™ technology and a Faster R-CNN to track and harvest sweet peppers as a test for helping fruit farmers.

Authored by admin Last updated on 08/02/2018 - 10:42
Offsite Link

A Fully Convolutional Model for Variable Bit Length and Lossy High-Density Compression of Mammograms

Using a convolutional autoencoder, a compression algorithm rivals JPEG and JPEG 2000 to reduce the size of mammogram images.

Authored by admin Last updated on 08/02/2018 - 10:42
Offsite Link

HeNet: A Deep Learning Approach on Intel® Processor Trace for Effective Exploit Detection

This paper presents a novel technique for detecting malware through classifying hardware-generated control flow traces using a deep neural network.

Authored by admin Last updated on 08/02/2018 - 11:03
Offsite Link

Highly Efficient 8-Bit, Low-Precision Inference of Convolutional Neural Networks

Get a detailed explanation of Intel® Optimization for Caffe, a deep learning framework supportive of 8-bit models to be used on Intel® Xeon® Scalable processors.

Authored by admin Last updated on 08/02/2018 - 11:07
Offsite Link

Integrate Multiplicative Features into Supervised Distributional Methods for Lexical Entailment

By adding multiplicative features into word-pair representations, linear and non-linear classifiers were found to have increased performance.

Authored by admin Last updated on 08/02/2018 - 11:10
Offsite Link

Interactive Image Segmentation with Latent Diversity

Bridging the gap between image segmentation and user-intended regions for applications, this method outperforms all prior approaches.

Authored by admin Last updated on 08/02/2018 - 11:12
Offsite Link

Learn to See in the Dark

This research uses convolutional neural networks to teach machines how to convert images taken in the dark into images in full light.

Authored by admin Last updated on 08/02/2018 - 11:15