Документация

 

Результаты поиска: 482

Уточнить по

    Результаты для:
Page icon

Performance Boosting in Seldon

Опубликовано: 11 июня 2019 г.Автор: Dariusz T.

The Seldon Core open source machine learning deployment platform facilitates management of inference pipelines

Getting Started with the Intel® NCS2 on Linux*

Последнее обновление: 6 июня 2019 г.Время видео: 3 мин

How to get started with the Intel® Neural Compute Stick 2 (Intel® NCS2) on Linux.

Analytics Zoo Introduction

Последнее обновление: 4 июня 2019 г.Время видео: 24 мин

Analytics Zoo is a unified analytics and AI platform, with Apache Spark*, BigDL, Tensorflow*, Keras.

Use Analytics Zoo Keras style API to solve classification problem

Последнее обновление: 31 мая 2019 г.Время видео: 11 мин

The tutorial shows Analytics Zoo Keras style API for classification problem. Analytics Zoo is a unified analytics and AI platform, with Apache Spark*, BigDL, Tensorflow*, Keras.

Use Analytics Zoo Keras Style API to Solve Regression Problems

Последнее обновление: 22 мая 2019 г.Время видео: 13 мин

The tutorial shows Analytics Zoo Keras style API for regression problems. Analytics Zoo is a unified analytics and AI platform, with Apache Spark*, BigDL, TensorFlow*, Keras.

Windows® 10 May 2019 Update for Machine Learning Acceleration on Intel® Integrated Graphics

Опубликовано: 17 мая 2019 г.Автор: Gokul Tonpe

Intel's earlier post in May 2018 introduced the Windows ML API and the DirectML API implementation on Intel® hardware via the DirectX 12 DirectCompute

Introduction to Natural Language Processing (NLP) Architect

Последнее обновление: 13 мая 2019 г.Время видео: 52 мин

This webinar focuses on introducing the audience to Natural Language Processing (NLP) Architect, a Python* library from the Intel® AI Lab for exploring the state-of-the-art deep learning topologies.

Intel® CPU Outperforms NVIDIA* GPU on ResNet-50 Deep Learning Inference

Опубликовано: 13 мая 2019 г.Автор: Haihao Shen

Intel Xeon processor outperforms NVidia's best GPUs on ResNet-50.

Introduction to the Intel® Distribution of OpenVINO™ Toolkit and Windows Machine Learning*

Последнее обновление: 13 мая 2019 г.Время видео: 1 мин

In this webinar you will learn how real-time inference on the PC for visual workloads such as object detection, recognition, and tracking are now easily developed with Intel® Distribution of OpenVINO™ Toolkit and Windows Machine Learning* API.

A City Surveillance Solution from GeoVision Inc.*

Последнее обновление: 10 мая 2019 г.Время видео: 1 мин

This solution uses Intel® Core™ i7 processors and supports up to four simultaneous video channels that perform facial recognition and tracking, plus gender recognition. This allows up to 40 humans to be processed concurrently.

Introducing the new Packed APIs for GEMM

Опубликовано: 18 августа 2016 г., обновлено 6 мая 2019 г.Автор: Gennady F.

1      Introducing Packed APIs for GEMM

Matrix-matrix multiplication (GEMM) is a fundamental operation in many scientific, engineering, and...

Detecting Acute Lymphoblastic Leukemia Using Caffe*, OpenVINO™ and Intel® Neural Compute Stick 2: Part 1

Опубликовано: 9 марта 2019 г., обновлено 29 апреля 2019 г.Автор: Milton-Barker, Adam

First part of a series that will take you through my experience building a custom classifier with Caffe* that should be able to detect AML/ALL.

Intel® DevCloud Published Datasets

Опубликовано: 26 апреля 2019 г.

The AI datasets described here were cleaned and preprocessed for use on the Intel® DevCloud. Includes descriptions, usage examples, keywords, and more

Object Detection: A Comparison of Performance of Deep Learning Models on Edge Using Intel® Movidius™ Neural Compute Stick and Raspberry PI* 3

Последнее обновление: 18 апреля 2019 г.

Vehicle Detection involves finding whether there is vehicle present or not secondly which type of vehicle is present and how many vehicles are...

Towards Privacy-Preserving Machine Learning

Последнее обновление: 18 апреля 2019 г.

When Artificial Intelligence involves some type of sensitive data, the problem is how to maintain the data privacy and security. This problem...

Implementing Attention Models in PyTorch*

Последнее обновление: 18 апреля 2019 г.

Recurrent Neural Networks have been the recent state-of-the-art methods for various problems whose available data is sequential in nature. Adding...

Distributed Training of Deep Learning Models with PyTorch*

Последнее обновление: 18 апреля 2019 г.

The motive of this article is to demonstrate the idea of distributed computing in the context of training large scale deep learning (DL) models....

Introduction to Reinforcement Learning Coach

Последнее обновление: 16 апреля 2019 г.Время видео: 50 мин

Introducing Reinforcement Learning (RL) Coach.

Transitioning from Intel® Movidius™ Neural Compute SDK to Intel® Distribution of OpenVINO™ toolkit

Опубликовано: 11 апреля 2019 г.Автор: Neal Smith

This article provides guidance for transitioning from the NCSDK to the Intel® Distribution of OpenVINO™ toolkit.

Code Sample: Intel® AVX512-Deep Learning Boost: Intrinsic Functions

Опубликовано: 2 апреля 2019 г.Автор: Alberto V.

How developers can use to take advantage of the new Intel® AVX512-Deep Learning Boost (Intel® AVX512-DL Boost) instructions.

Intel and Facebook* collaborate to boost PyTorch* CPU performance

Опубликовано: 2 апреля 2019 г.Автор: Andres Rodriguez

Intel's software optimization and 2nd generation Intel® Xeon® Scalable Processors with Intel® DL Boost® accelerate PyTorch's CPU performance

Page icon

Second Generation Intel® Xeon® Processor Scalable Family Technical Overview

Опубликовано: 2 апреля 2019 г.Автор: David Mulnix

New features and enhancements available in the second generation Intel® Xeon® processor Scalable family and how developers can take advantage of them

Getting Started with Intel® Optimization for PyTorch* on Second Generation Intel® Xeon® Scalable Processors

Accelerate deep learning PyTorch* code on second generation Intel® Xeon® Scalable processor with Intel® Deep Learning Boost.

Detecting Acute Lymphoblastic Leukemia Using Caffe*, OpenVINO™ and Intel® Neural Compute Stick 2: Part 2

In this article I will cover the steps required to create the dataset required to train the model using the network we defined in the last tutorial.

Reducing False Negatives in the Invasive Ductal Carcinoma Classifier

Опубликовано: 18 июня 2018 г., обновлено 15 марта 2019 г.Автор: Milton-Barker, Adam

This project tries to trick the model by using very similar, but opposite class, images from a small set of testing data that we believe humans may...

Intel® Math Kernel Library Improved Small Matrix Performance Using Just-in-Time (JIT) Code Generation for Matrix Multiplication (GEMM)

Опубликовано: 6 сентября 2018 г., обновлено 15 марта 2019 г.Автор: Gennady F.

    The most commonly used and performance-critical Intel® Math Kernel Library (Intel® MKL) functions are the general matrix multiply (GEMM)...

Getting to Know the Intel® Neural Compute Stick 2

Последнее обновление: 13 марта 2019 г.Время видео: 48 мин

In this webinar you’ll get an overview of the Intel® Neural Compute Stick 2 (Intel® NCS 2), what it is good for, and see how easy it is to get started.

Acute Myeloid/Lymphoblastic Leukemia Data Augmentation

The AML/ALL Classifier Data Augmentation program applies filters to datasets and increases the amount of training and test data available to use.

Page icon

How AI is Helping Us Better Understand the Environment

Опубликовано: 5 марта 2019 г.

Success Story: Researchers use AI techniques to help understand ecosystems better to analyze the complex interactions and patterns in our environment.

Deep Learning with Analytic Zoo Optimizes Mastercard* Recommender AI Service

Опубликовано: 4 марта 2019 г.Автор: Yang, Yuhao

Introduces a joint initiative between Mastercard* and Intel in building users-items propensity models for a universal recommender AI service.

Page icon

Computer Vision Annotation Tool: A Universal Approach to Data Annotation

Опубликовано: 1 марта 2019 г.Автор: Sekachev, Boris

At Intel, one of the projects we’re undertaking research on is developing computer vision algorithms based on deep neural networks (DNNs) and how...

Intel booth at convention

Harness the Power of Data from Connected Things

Опубликовано: 26 февраля 2019 г.Автор: DANIELA M.

With interoperable building blocks, purpose-built silicon, software tools, and ecosystem support, you can accelerate your development of IoT solutions

Talroo* Uses Analytics Zoo and AWS* to Leverage Deep Learning for Job Recommendations

Опубликовано: 25 февраля 2019 г.Автор: Song, Guoqiong

This project demonstrates how to leverage the natural language context analysis and recommender models of Analytics Zoo on Amazon Web Services (AWS*)

Detecting Invasive Ductal Carcinoma with Convolutional Neural Networks

Опубликовано: 3 мая 2018 г., обновлено 20 февраля 2019 г.Автор: Milton-Barker, Adam

This article, Machine Learning and Mammography, shows how existing deep learning technologies can be utilized to train artificial intelligence (AI)...

Flower

Identify Plant Anatomy Using the Intel® Distribution of OpenVINO™ Toolkit

Опубликовано: 20 февраля 2019 г.Автор: Biswas, Risab

Use Case: Build a model to identify plant anatomy with the Intel® Distribution of OpenVINO™ Toolkit

Страницы