DEEP LEARNING WITH STRUCTURE


Charlie Tang is a PhD student in the Machine Learning group at the University of Toronto, working with Geoffrey Hinton and Ruslan Salakhutdinov, whose research interests include machine learning, computer vision and cognitive science. More specifically, he has developed various higher-order extensions to generative models in deep learning for vision.

At the Deep Learning Summit in Boston next month, Charlie will present 'Deep Learning with Structure'. Supervised neural networks trained on massive datasets have recently achieved impressive performance in computer vision, speech recognition, and many other tasks. While extremely flexible, neural nets are often criticized because their internal representations are distributed codes and lack interpretability; during his presentation at the summit, Charlie will reveal how we can address some of these concerns.

We had a quick Q&A with Charlie ahead of the Deep Learning Summit, to hear more of his thoughts on developments and challenges in deep learning.

What are the key factors that have enabled recent advancements in deep learning? 
The three key factors are:
- The steadfast belief and knowledge that supervised neural networks trained with enough labelled data can achieve great test set generalization.
- The availability of high performance hardware and software, in particular, Nvidia's CUDA architecture and SDK. This allowed more experimentation and the learning from large-scale data.
- The development of superior models: switching to rectified linear hidden units from the sigmoid or hyperbolic tangent units and the invention of regularization techniques, specifically "Dropout".

What are the main types of problems now being addressed in the deep learning space? 
Almost all problems in statistical machine learning are currently being investigated using deep learning techniques. They include visual and speech recognition, reinforcement learning, natural language processing, medical and health applications, financial engineering and many others.

What are the practical applications of your work and what sectors are most likely to be affected?
The deep learning revolution allows models trained on big data to drastically improve accuracy. This means that many artificial intelligence recognition tasks can be now automated, which previously necessitated a human in-the-loop.

What developments can we expect to see in deep learning in the next 5 years?
Deep learning algorithms will be gradually adopted for more tasks and will "solve" more problems. For example, 5 years ago, algorithmic face recognition accuracy was still somewhat worse than human performance. However, currently, super-human performances are reported on the main face recognition dataset (LFW) and the standard image classification dataset (Imagenet). In the next 5 years, harder and harder problems such as video recognition, medical imaging or text processing will be successfully tackled by deep learning algorithms. We can also expect deep learning algorithms to be ported to commercial products, much like how the face detector was incorporated into consumer cameras in the past 10 years.

What advancements excite you most in the field?
I feel like the most exciting advance is the availability of low-energy mobile hardware that supports deep learning algorithms. This will inevitably lead to many real-time systems and mobile products which will be a part of our daily lives.

The Deep Learning Summit is taking place in Boston on 26-27 May. For more information and to register, please visit the event website here.

Join the conversation with the event hashtag #reworkDL

DEEP LEARNING WITH STRUCTURE的更多相关文章

  1. Can deep learning help you find the perfect girl?

    Can deep learning help you find the perfect girl? One of the first things I did when I moved to Mont ...

  2. (转) Awesome Deep Learning

    Awesome Deep Learning  Table of Contents Free Online Books Courses Videos and Lectures Papers Tutori ...

  3. (转) The major advancements in Deep Learning in 2016

    The major advancements in Deep Learning in 2016 Pablo Tue, Dec 6, 2016 in MACHINE LEARNING DEEP LEAR ...

  4. (转) Deep Learning Research Review Week 2: Reinforcement Learning

      Deep Learning Research Review Week 2: Reinforcement Learning 转载自: https://adeshpande3.github.io/ad ...

  5. (转)Deep Learning Research Review Week 1: Generative Adversarial Nets

    Adit Deshpande CS Undergrad at UCLA ('19) Blog About Resume Deep Learning Research Review Week 1: Ge ...

  6. (转) Deep Learning in a Nutshell: Core Concepts

    Deep Learning in a Nutshell: Core Concepts Share:   Posted on November 3, 2015by Tim Dettmers 7 Comm ...

  7. (转)The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3)

    Adit Deshpande CS Undergrad at UCLA ('19) Blog About The 9 Deep Learning Papers You Need To Know Abo ...

  8. Applied Deep Learning Resources

    Applied Deep Learning Resources A collection of research articles, blog posts, slides and code snipp ...

  9. Machine and Deep Learning with Python

    Machine and Deep Learning with Python Education Tutorials and courses Supervised learning superstiti ...

随机推荐

  1. 微软职位内部推荐-UX Designer II

    微软近期Open的职位: Search Technology Center Asia (STCA) Position: UX Designer Location: Beijing, China Sea ...

  2. Linux 进程通信(共享内存区)

    共享内存是由内核出于在多个进程间交换信息的目的而留出的一块内存区(段). 如果段的权限设置恰当,每个要访问该段内存的进程都可以把它映像到自己的私有地址空间中. 如果一个进程更新了段中的数据,其他进程也 ...

  3. 使用js使某个按钮在5秒内不能重复点击

    <head> <!--参考:http://illy.iteye.com/blog/1534276 --> <!-- http://y.dobit.top/Detail/1 ...

  4. 不可不知的C#基础 4. 延迟加载 -- 提高性能

    延迟加载(lazy loading) 设计模式是为了避免一些无谓的性能开销而提出来的,所谓延迟加载就是当在真正需要数据(读取属性值)的时候,才真正执行数据加载操作. 有效使用它可以大大提高系统性能. ...

  5. js window.open()实现打印,如何在关闭打印窗口时刷新父窗口

    var childWin = window.open("your URL"); //获取子窗口句柄childWin.onunload = function(){ //onunloa ...

  6. ViewConfiguration.getScaledTouchSlop () 用法

    getScaledTouchSlop是一个距离,表示滑动的时候,手的移动要大于这个距离才开始移动控件.如果小于这个距离就不触发移动控件,如viewpager就是用这个距离来判断用户是否翻页 ViewC ...

  7. xcode 出现the file couldn't be opened 怎么解决

    右键——show In finder——显示xcode包内容——将有数字的删除——把有用的xcode双击

  8. 20145222黄亚奇《Java程序设计》第1周学习总结

    教材学习内容总结 BJVM是Java程序唯一认识的操作系统,其可执行文件为.class文档 Java的三大平台为Java SE,Java EE,Java ME. Java SE的四个部分为:JVM,J ...

  9. 清除sql server 登录的时候记住的账户

    SQl 2008如何清除登陆过的服务器名称   C:\Users\Administrator\AppData\Roaming\Microsoft\Microsoft SQL Server\100\To ...

  10. 好玩的Prim算法

    这段时间学算法,用JS实现了一个Prim,用于在连通图中找出最小树,具体内容.代码解析周末会不上,现在先把源码献上: <!DOCTYPE html> <html charset='G ...