December 6, 2019

197 words 1 min read

Chainer: A flexible and intuitive framework for complex neural networks

Chainer: A flexible and intuitive framework for complex neural networks

Open source software frameworks are the key for applying deep learning technologies. Orion Wolfe and Shohei Hido introduce Chainer, a Python-based standalone framework that enables users to intuitively implement many kinds of other models, including recurrent neural networks, with a lot of flexibility and comparable performance to GPUs.
Talk Title Chainer: A flexible and intuitive framework for complex neural networks
Speakers Orion Wolfe (Preferred Networks), Shohei Hido (Preferred Networks)
Conference O’Reilly Artificial Intelligence Conference
Conf Tag
Location New York, New York
Date September 26-27, 2016
URL Talk Page
Slides Talk Slides
Video

Open source software frameworks are the key for applying deep learning technologies. Due to the success of Caffe, Torch, Theano, and TensorFlow, the power of deep learning continues to expand beyond traditional pattern recognition tasks such as image recognition. However, the gap is rapidly increasing between the complexities of newly proposed neural network models and the capabilities of existing frameworks, which have been mainly used for convolutional neural networks. Orion Wolfe and Shohei Hido introduce Chainer, a Python-based standalone framework that enables users to intuitively implement many kinds of other models, including recurrent neural networks, with a lot of flexibility and comparable performance to GPUs.

recurrent neural network framework network model gpu performance tensorflow open source network deep learning python neural network
comments powered by Disqus
Deeply active learning: Approximating human learning with smaller datasets combined with human assistance

Deeply active learning: Approximating human learning with smaller datasets combined with human assistance

December 6, 2019

Natural-language assistants are the emergent killer app for AI. Getting from here to there with deep learning, however, can require enormous datasets. Christopher Nguyen and Binh Han explain how to shorten the time to effectiveness and the amount of training data that's required to achieve a given level of performance using human-in-the-loop active learning.
TensorFlow: Machine learning for everyone

TensorFlow: Machine learning for everyone

November 17, 2019

TensorFlow is an open source software library for numerical computation with a focus on machine learning. Its flexible architecture makes it great for research and production deployment. Sherry Moore offers a high-level introduction to TensorFlow and explains how to use it to train machine-learning models to make your next application smarter.
Navigating the data science Python ecosystem

Navigating the data science Python ecosystem

November 7, 2019

Python's popularity for data science use cases has skyrocketed in recent years due to its ease of use, great developer and user community, and solid core of scientific libraries. Christine Doig explores data science and the state of the Python ecosystem and helps navigate the large amount of open source libraries available for data science in Python, providing a map to guide you on the journey.
TensorFlow: Machine learning for everyone

TensorFlow: Machine learning for everyone

October 20, 2019

TensorFlow is an open source software library for numerical computation with a focus on machine learning. Rajat Monga offers an introduction to TensorFlow and explains how to use it to train and deploy machine-learning models to make your next application smarter.
Deep neural network model compression and an efficient inference engine

Deep neural network model compression and an efficient inference engine

December 6, 2019

Neural networks are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. Song Han explains how deep compression addresses this limitation by reducing the storage requirement of neural networks without affecting their accuracy and proposes an energy-efficient inference engine (EIE) that works with this model.
Lessons learned from deploying the top deep learning frameworks in production

Lessons learned from deploying the top deep learning frameworks in production

December 6, 2019

By building a marketplace for algorithms, Algorithmia gained unique experience with building and deploying machine-learning models using a wide variety of frameworks. Kenny Daniel shares the lessons Algorithmia learned through trial and error, the pros and cons of different deep learning frameworks, and the challenges involved with deploying them in production systems.