LIBRARY

230 Search Results

Refine by

    Results for:

Visualising CNN Models Using PyTorch*

And no, you don’t need a GPU to test your model. Before any of the deep learning systems came along, researchers took a painstaking amount of time...

Object Detection on Drone Videos using Neon™ Framework

Abstract The purpose of this article is to showcase the implementation of object detection1 on drone videos using Intel® optimized framework for...

Object Detection on Drone Videos using Caffe* Framework

Abstract The purpose of this article is to showcase the implementation of object detection1 on drone videos using Intel® Optimization for Caffe*2 on...

Face Detection with Intel® Distribution for Python*

Abstract Artificial Intelligence (AI) can be used to solve a wide range of problems, including those related to computer vision, such as image...

Pedestrian Detection Using Deep Neural Networks on Intel® Architecture

Published on January 30, 2018

Abstract This paper explains the process to train and infer the pedestrian detection problem using the TensorFlow* deep learning framework on Intel...

Intel® Math Kernel Library for Deep Learning Networks: Part 1–Overview and Installation

Learn how to install and build the library components of the Intel MKL for Deep Neural Networks.

Manage Deep Learning Networks with Intel® Optimization for Chainer*

Summary Chainer* is a Python*-based deep learning framework aiming at flexibility and intuition. It provides automatic differentiation APIs based...

Traffic Light Detection Using the TensorFlow* Object Detection API

Published on January 26, 2018

Abstract This case study evaluates the ability of the TensorFlow* Object Detection API to solve a real-time problem such as traffic light detection...

Deep Learning for Cancer Diagnosis: A Bright Future

In this article we explore how deep learning has been successfully applied to potential areas of oncology (the study of cancer diagnosis and...

Introducing DNN primitives in Intel® Math Kernel Library

    Deep Neural Networks (DNNs) are on the cutting edge of the Machine Learning domain. These algorithms received wide industry adoption in the late...

Review of Architecture and Optimization on Intel® Xeon® Scalable Processors in context of Intel® Optimized TensorFlow* on Intel® AI DevCloud

When I joined the Intel® Student Developer Program in late 2017 I was pretty excited to try the Intel® Xeon® scalable processor[1] that is a part of...

Boosting Deep Learning Training & Inference Performance on Intel® Xeon® and Intel® Xeon Phi™ Processors

View PDF In this work we present how, without a single line of code change in the framework, we can further boost the performance for deep learning...

Lower Numerical Precision Deep Learning Inference and Training

View PDF Introduction Most commercial deep learning applications today use 32-bits of floating point precision (ƒp32) for training and inference...

Build an Image Classifier in 5 steps on the Intel® Movidius™ Neural Compute Stick

What is Image Classification? Image classification is a computer vision problem that aims to classify a subject or an object present in an image...

Using the CPU for Effective and Efficient Medical Image Analysis

A Quantitative Report Based on the Alibaba Tianchi Healthcare AI Competition 2017 Overview This paper is based on the Tianchi Healthcare AI...

Accelerating AI from the Cloud to the Edge

Last updated: January 5, 2018Video length: 1 hr

Learn how Intel can help you develop applications & solutions for the next big technology wave.

AI News | January 2018

Last updated: January 4, 2018Video length: 1 min

WELCOME TO 2018! In this episode you'll see the world’s first neural network processor, get a look at a new deep learning edge solution, and we explore Unity Technologies’ ML-Agents exclusively on Intel Architecture!

Accelerating Deep Learning Training with BigDL and Drizzle on Apache Spark*

In recent years, the scale of datasets and models used in deep learning has increased dramatically. Although larger datasets and models can improve...

Testing of Six Different AI-Based Models: A Deep Dive to Improve Cervical Cancer Screening

Published on January 2, 2018

Team GRXJ Seeks to Make a Difference, Using AI to Improve Cervical Cancer Screening Editor’s note: This is one in a series of case studies...

Intel® Processors for Deep Learning Training

On November 7, 2017, UC Berkeley, U-Texas, and UC Davis researchers published their results training ResNet-50* in a record time (as of the time of...

How Can AI Advance Cervical Cancer Detection Using Convolutional Neural Networks

Published on December 28, 2017

Indrayana Rustandi Employs Convolutional Neural Networks to Improve Cervical Cancer Screening Editor’s note: This is one in a series of case studies...

Art’Em – Artistic Style Transfer to Virtual Reality Final Update

Art’Em is an application that uses computer vision to bring artistic style transfer to real time speeds in VR compatible resolutions. This program...

Deep Learning Improves Cervical Cancer Accuracy by 81%, Using Intel Technology

Published on December 22, 2017

Kaggle* Master Silva Develops Two AI Solutions to Improve the Precision and Accuracy of Cervical Cancer Screening Editor's note: This is one in a...

Faster Convolutional Neural Network Models Improve the Screening of Cervical Cancer

Published on December 22, 2017

A Lithuanian Team Tests the Capabilities of AI to Improve Cervical Cancer Screening Editor's note: This is one in a series of case studies...

Hands-On AI Part 24: TensorFlow* Serving for AI API and Web App Deployment

Published on December 19, 2017

A Tutorial Series for Software Developers, Data Scientists, and Data Center Managers Welcome to the final article in the hands-on AI tutorial series...

Installing and Building MXNet with Intel® MKL

The latest version of MXNet includes built-in support for the Intel® Math Kernel Library (Intel® MKL) 2018. The latest version of the Intel MKL...

CIFAR-10 Classification using Intel® Optimization for TensorFlow*

Published on December 12, 2017

Abstract This work demonstrates the experiments to train and test the deep learning AlexNet* topology with the Intel® Optimization for TensorFlow*...

How to Get Started Developing for Automated Driving

Published on December 13, 2016, updated December 12, 2017

From safe roads to enjoyable commutes, automated driving is poised to change lives and society for the better. As the car moves to the center of the...

Finding Missing Kids through Code

This article describes how Intel is contributing to the facial recognition component of Child Finder Service*. We hope that people from a broad range...

Power System Infrastructure Monitoring Using Deep Learning on Intel® Architecture

Published on July 14, 2017, updated December 11, 2017

This paper evaluates the performance of Intel® Xeon® processor powered machines for running deep learning on the GoogleNet* topology (Inception* v3...

Manufacturing Package Fault Detection Using Deep Learning

Executive Summary Intel's Software and Services Group engineers recently worked with assembly and test factory engineers on a proof of concept...

AI News: December 2017

Last updated: December 7, 2017Video length: 1 min

In this episode you will get a look at deep neural networks and how they are being used to identify unattended baggage for new security. How deep learning could be used to discover crypto-currency trader sentiment. You'll also learn what Intel student ambassador Panuwat is doing in AI research.

Intel® Distribution for Python* versus Non-Optimized Python: Breast Cancer Classification

Published on December 6, 2017

Abstract This case study compares the performance of Intel® Distribution for Python* to that of non-optimized Python using a breast cancer...

Explore Unity Technologies ML-Agents* Exclusively on Intel® Architecture

This article describes how to install and run Unity Technologies ML-Agents* in CPU-only environments. It demonstrates how to: train and run the ML-...

Automatic Defect Inspection Using Deep Learning for Solar Farm

Executive Summary Intel's Software and Services Group (SSG) engineers recently collaborated with Intel's New Technology Group (NTG) to launch a...

Pages