Deep Learning: A Practitioner's Approach NEW!
An effective deep learning development process is critical for widespread industrial adoption, particularly in the automotive sector. A typical industrial deep learning development cycle involves customizing and re-designing an off-the-shelf network architecture to meet the operational requirements of the target application, leading to considerable trial and error work by a machine learning practitioner. This approach greatly impedes development with a long turnaround time and the unsatisfactory quality of the created models. As a result, a development platform that can aid engineers in greatly accelerating the design and production of compact, optimized deep neural networks is highly desirable. In this joint industrial case study, we study the efficacy of the GenSynth AI-assisted AI design platform for accelerating the design of custom, optimized deep neural networks for autonomous driving through human-machine collaborative design. We perform a quantitative examination by evaluating 10 different compact deep neural networks produced by GenSynth for the purpose of object detection via a NASNet-based user network prototype design, targeted at a low-cost GPU-based accelerated embedded system. Furthermore, we quantitatively assess the talent hours and GPU processing hours used by the GenSynth process and three other approaches based on the typical industrial development process. In addition, we quantify the annual cloud cost savings for comprehensive testing using networks produced by GenSynth. Finally, we assess the usability and merits of the GenSynth process through user feedback. The findings of this case study showed that GenSynth is easy to use and can be effective at accelerating the design and production of compact, customized deep neural network.
Deep Learning: A Practitioner's Approach
Download File: https://www.google.com/url?q=https%3A%2F%2Ftinourl.com%2F2ufRZN&sa=D&sntz=1&usg=AOvVaw2_MaKMQ1qvNnMdDPceNfup
CMU-CS-19-109Differentiable Optimization-Based Modeling for Machine LearningBrandon AmosPh.D. ThesisMay 2019CMU-CS-19-109.pdfKeywords: Machine learning, statistical modeling, convex optimization, deep learning,control, reinforcement learningDomain-specific modeling priors and specialized components are becoming increasingly important to the machine learning field. These components integrate specialized knowledge that we have as humans into model. We argue in this thesis that optimization methods provide an expressive set of operations that should be part of the machine learning practitioner's modeling toolbox.We present two foundational approaches for optimization-based modeling:1) the OptNet architecture that integrates optimization problems as individual layers in larger end-to-end trainable deep networks, and 2) the input-convex neural network (ICNN) architecture that helps make inference and learning in deep energy-based models and structured prediction more tractable.We then show how to use the OptNet approach 1) as a way of combining model-free and model-based reinforcement learning and 2) for top-@i learning problems. We conclude by showing how to differentiate cone programs and turn the cvxpy domain specific language into a differentiable optimization layer that enables rapid prototyping of the approaches in this thesis.The source code for this thesis document is available in open source form.147 pagesThesis Committee:J. Zico Kolter (Chair)Barnabás PóczosJeff Schneider Vladlen Koltun (Intel Labs)Srinivasan Seshan, Head, Computer Science DepartmentTom M. Mitchell, Interim Dean, School of Computer Science Return to: SCS Technical Report CollectionSchool of Computer Science This page maintained by reports@cs.cmu.edu
Other tools to automatically detect sleep apnea through at-home devices exist using computer models built either through traditional machine learning methods, which rely on knowledge from human experts to design hand-creafted features that can identify sleep apnea conditions in a data set, or through deep learning methods, which eliminate the need for such experts due to immense amounts of data. But, according to Huang, there are limitations to these standalone approaches. 041b061a72