December 6, 2019

155 words 1 min read

Deep learning: Modular in theory, inflexible in practice

Deep learning: Modular in theory, inflexible in practice

The high-level view of deep learning is elegant: composing differentiable components together trained in an end-to-end fashion. The reality isn't that simple, and the commonly used tools greatly limit what we are capable of doing. Diogo Almeida explains what we can do about it and offers a practical attempt at a deep learning library of the future.
Talk Title Deep learning: Modular in theory, inflexible in practice
Speakers Diogo Moitinho de Almeida (Enlitic)
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

The high-level view of deep learning is elegant: composing differentiable components together trained in an end-to-end fashion. The reality isn’t that simple, and the commonly used tools greatly limit what we are capable of doing. Diogo Almeida explains what we can do about it and offers a practical attempt at a deep learning library of the future. Topics include:

deep learning
comments powered by Disqus
Chainer: A flexible and intuitive framework for complex neural networks

Chainer: A flexible and intuitive framework for complex neural networks

December 6, 2019

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.
Deep learning at scale and use cases

Deep learning at scale and use cases

December 6, 2019

Deep learning has made a major impact in the last three years. Imperfect interactions with machines, such as speech or image processing, have been made robust by deep learning that finds usable structure in large datasets. Naveen Rao outlines deep learning challenges and explores how changes to the organization of computation and communication can lead to advances in capabilities.
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.
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.
Obstacles to progress in AI

Obstacles to progress in AI

December 5, 2019

The essence of intelligence is the ability to predict. Prediction, perception, planning/reasoning, attention, and memory are the pillars of intelligence. Yann LeCun describes several projects at FAIR and NYU on unsupervised learning, question answering with a new type of memory-augmented network, and various applications for vision and natural language understanding.
Progress of delivering real AI workloads

Progress of delivering real AI workloads

December 5, 2019

Progress in enterprise AI workloads, particularly in deep learning, big data, and computing infrastructure, will profoundly impact productivity for users. XD Huang outlines enterprise AI examples to illustrate the collective efforts and exciting opportunities modern AI technologies are making possible.