Microsoft releases version 2.0 of its deep learning toolkit

Microsoft releases version 2.0 of its deep learning toolkit  #CompBindTech

  • Microsoft today launched version 2.0 of what is now called the Microsoft Cognitive Toolkit.
  • This open-source toolkit, which was previously known as CNTK, is Microsoft’s competitor to similar tools like TensorFlow, Caffe and Torch, and, while the first version was able to challenge many of its competitors in terms of speed, this second version puts an emphasis on usability (by adding support for Python and the popular Keras neural networking library, for example) and future extensibility, while still maintaining — and improving — its speed.
  • Because it was essentially an internal tool, though, it didn’t support Python for example, even though it’s by far the most popular language among machine learning Microsoft originally built this toolkit for speech recognition systems, it was very good at working with time series data for building recurrent neural nets.
  • Huang stressed that the first version of the Cognitive Toolkit outperformed its competitors pretty easily on a number of standard tests.
  • Unsurprisingly, Microsoft is stressing the fact that the Cognitive Toolkit is a battle-tested system that it uses to power most of its internal AI systems, including Cortana, and that it can train models faster than most of its competitors.

Microsoft today launched version 2.0 of what is now called the Microsoft Cognitive Toolkit. This open-source toolkit, which was previously known as CNTK, is..
Continue reading “Microsoft releases version 2.0 of its deep learning toolkit”

Enterprise Software Tools for AI

  • The complete report, available here, covers how businesses are using machine learning and deep learning, differentiating between AI, machine learning and deep learning, what it takes to get started, software tools for AI and more.
  • There are three exemplary members of the AI software stack available as deep learning frameworks: Caffe, MXNet and TensorFlow.
  • • MXNet, jointly developed by collaborators from multiple universities and companies, is a lightweight, portable and flexible deep learning framework designed for both efficiency and flexibility.
  • Enterprise software tools for AI also includes NVIDIA DIGITS , which puts the power of deep learning into the hands of engineers and data scientists.
  • DIGITS simplifies common deep learning tasks such as managing data, designing and training neural networks on multi-GPU systems, monitoring performance in real time with advanced visualizations, and selecting the best performing model.

There are three exemplary members of the AI software stack available as deep learning frameworks. This post explores software options for AI.
Continue reading “Enterprise Software Tools for AI”

AI Tech Talk: An Overview of AI on the AWS Platform

New on the AWS #AI Blog,

  • AWS offers a family of intelligent services that provide cloud-native machine learning and deep learning technologies to address your different use cases and needs.
  • For developers looking to add managed AI services to their applications, AWS brings natural language understanding (NLU) and automatic speech recognition (ASR) with Amazon Lex, visual search and image recognition with Amazon Rekognition, text-to-speech (TTS) with Amazon Polly, and developer-focused machine learning with Amazon Machine Learning.
  • For more in-depth deep learning applications, the AWS Deep Learning AMI lets you run deep learning in the cloud, at any scale.
  • Launch instances of the AMI, pre-installed with open source deep learning frameworks (Apache MXNet, TensorFlow, Caffe, Theano, Torch and Keras), to train sophisticated, custom AI models, experiment with new algorithms, and learn new deep learning skills and techniques; all backed by auto-scaling clusters of GPU-based instances.
  • Whether you’re just getting started with AI or you’re a deep learning expert, this session will provide a meaningful overview of the managed AI services, the AI Platform offerings, and the AI Frameworks you can run on the AWS Cloud.

AWS offers a family of intelligent services that provide cloud-native machine learning and deep learning technologies to address your different use cases and needs. For developers looking to add managed AI services to their applications, AWS brings natural language understanding (NLU) and automatic speech recognition (ASR) with Amazon Lex, visual search and image recognition with Amazon Rekognition, text-to-speech (TTS) with Amazon Polly, and developer-focused machine learning with Amazon Machine Learning.
Continue reading “AI Tech Talk: An Overview of AI on the AWS Platform”

An overview of gradient descent optimization algorithms

An overview of gradient descent optimization algorithms #deeplearning #abdsc

  • We will consider additional strategies that are helpful for optimizing gradient descent.
  • You need to be a member of Data Science Central to add comments!
  • We will also take a short look at algorithms and architectures to optimize gradient descent in a parallel and distributed setting.
  • Every state-of-the-art Deep Learning library contains implementations of various algorithms to optimize gradient descent (e.g. lasagne’s , caffe’s , and keras’ documentation).
  • If you are unfamiliar with gradient descent, you can find a good introduction on optimizing neural networks .

This article was written by Sebastian Ruder. Sebastian is a PhD student in Natural Language Processing and a research scientist at AYLIEN. He blogs about Machi…
Continue reading “An overview of gradient descent optimization algorithms”

Deep Learning Frameworks

New #cuDNN 5.1, 2.7x faster training of #deeplearning networks with 3x3 convolutions.

  • Deep learning course: Getting Started with the Caffe Framework
  • Choose a deep learning framework from the list below, download the supported version of cuDNN and follow the instructions on the framework page to get started.
  • Chainer is a deep learning framework that’s designed on the principle of define-by-run.
  • Caffe is a deep learning framework made with expression, speed, and modularity in mind.

Read the full article, click here.


@GPUComputing: “New #cuDNN 5.1, 2.7x faster training of #deeplearning networks with 3×3 convolutions.”


The NVIDIA Deep Learning SDK accelerates widely-used deep learning frameworks such as Caffe, CNTK, TensorFlow, Theano and Torch as well as many other deep learning applications. Choose a deep learning framework from the list below, download the supported version of cuDNN and follow the instructions on the framework page to get started.


Deep Learning Frameworks

Deep learning tutorial on Caffe technology : basic commands, Python and C++ code.

#Deeplearning tutorial on #Caffe technology : basic commands, #Python and C++ code

  • ‘Data’ : for data saved in a LMDB database, such as before
  • net.blobs[‘data’] contains input data, an array of shape (1, 1, 100, 100) net.blobs[‘conv’] contains computed data in layer ‘conv’ (1, 3, 96, 96)
  • Learn : solve the params on training data
  • /data/ilsvrc12/get_ilsvrc_aux.sh #have a look at the model python python/draw_net.py models/bvlc_reference_caffenet/deploy.prototxt caffenet.png open caffenet.png
  • Let’s create a layer to add a value.

Read the full article, click here.


@deeplearningldn: “#Deeplearning tutorial on #Caffe technology : basic commands, #Python and C++ code”


Disrupting SASU. Christopher Bourez


Deep learning tutorial on Caffe technology : basic commands, Python and C++ code.

Deep learning tutorial on Caffe technology : basic commands, Python and C++ code.

#DeepLearning tutorial on Caffe technology: basic commands, #Python and C++ code

  • ‘Data’ : for data saved in a LMDB database, such as before
  • net.blobs[‘data’] contains input data, an array of shape (1, 1, 100, 100) net.blobs[‘conv’] contains computed data in layer ‘conv’ (1, 3, 96, 96)
  • Learn : solve the params on training data
  • /data/ilsvrc12/get_ilsvrc_aux.sh #have a look at the model python python/draw_net.py models/bvlc_reference_caffenet/deploy.prototxt caffenet.png open caffenet.png
  • Let’s create a layer to add a value.

Read the full article, click here.


@kdnuggets: “#DeepLearning tutorial on Caffe technology: basic commands, #Python and C++ code”


Disrupting SASU. Christopher Bourez


Deep learning tutorial on Caffe technology : basic commands, Python and C++ code.