(Stay tuned, I keep updating this post while I plow in my deep learning garden:))
in category: Machine Learning vs Deep Learning
*****The following slide is from slideshare.net: Transfer Learning and Fine-tuning Deep Neural Networks (Sep 2, 2016 by Anusua Trivedi, Data Scientist @ Microsoft)
*****The following slide is from Prof. Andrew Ng’s talk “Machine Learning and AI via Brain simulations” (PDF) at Stanford University.
*****The following slide is from the lecture talk “How Could Machines Learn as Efficiently as Animals and Humans?” (December 12, 2017) given by Prof. Yann LeCun, Director of Facebook AI Research and Silver Professor of Computer Science at New York University.
*****Below is an excerpt from What is deep learning? (By Jason Brownlee on August 16, 2016)
The core of deep learning according to Andrew is that we now have fast enough computers and enough data to actually train large neural networks. When discussing why now is the time that deep learning is taking off at ExtractConf 2015 in a talk titled “What data scientists should know about deep learning“, he commented:
very large neural networks we can now have and … huge amounts of data that we have access to
He also commented on the important point that it is all about scale. That as we construct larger neural networks and train them with more and more data, their performance continues to increase. This is generally different to other machine learning techniques that reach a plateau in performance.
for most flavors of the old generations of learning algorithms … performance will plateau. … deep learning … is the first class of algorithms … that is scalable. … performance just keeps getting better as you feed them more data
Dr. Andrew Ng provides a nice plot in his slides:
(Source: Ng, A. What Data Scientists Should Know about Deep Learning (see slide 30 of 34), 2015)
*****The relations between AI, Machine Learning, and Deep Learning
“Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth.” (check here for source.)
Below is a short excerpt from the source: The AI Revolution: Why Deep Learning Is Suddenly Changing Your Life (from fortune.com By Roger Parloff, Illustration by Justin Metz on SEPTEMBER 28, 2016)
Think of deep learning as a subset of a subset. “Artificial intelligence” encompasses a vast range of technologies—like traditional logic and rules-based systems—that enable computers and robots to solve problems in ways that at least superficially resemble thinking. Within that realm is a smaller category called machine learning, which is the name for a whole toolbox of arcane but important mathematical techniques that enable computers to improve at performing tasks with experience. Finally, within machine learning is the smaller subcategory called deep learning.
A detailed explanation similar to the nested set diagram above can be found in this post Understanding the differences between AI, machine learning, and deep learning (By Hope Reese | February 23, 2017).
======Below are some main screenshots from this talk: Watch Now: Deep Learning Demystified
References and reading list:
- slideshare.net: Transfer Learning and Fine-tuning Deep Neural Networks (Sep 2, 2016 by Anusua Trivedi, Data Scientist @ Microsoft)
- What is deep learning? (by Jason Brownlee on August 16, 2016)
- The AI Revolution: Why Deep Learning Is Suddenly Changing Your Life (from fortune.com by Roger Parloff, Illustration by Justin Metz on SEPTEMBER 28, 2016)
- Watch Now: Deep Learning Demystified (YouTube, Uploaded on Mar 30, 2017)
- Understanding the differences between AI, machine learning, and deep learning (by Hope Reese | February 23, 2017) — pdf
- Artificial Intelligence, Machine Learning and Deep Learning
- Machine Learning vs. Deep Learning (August 22, 2017)
- Deep Learning vs. Machine Learning – the essential differences you need to know (April 8, 2017 )
- Feature Engineering on SlideShare (by HJ van Veen, Published on Feb 20, 2017) — Tips & Tricks for Feature Engineering / Applied Machine Learning.
- Discover Feature Engineering, How to Engineer Features and How to Get Good at It (by Jason Brownlee on September 26, 2014 )
- Theoretical Machine Learning Lecture Series: How Could Machines Learn as Efficiently as Animals and Humans? (by Yann LeCun, December 12, 2017)