Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
What it is
Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.
Why Hacker News recommends it
HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.
- 9 people recommended it
- 7 different months
- 6 strong recommendations
- first 2011, last 2013
What HN commenters said
“Here's a great talk by Andrew Ng of Stanford”
Conveys the excitement and potential of unsupervised feature learning.
apu, 2011-05 · Strong recommendation · in “Neural Networks making a come-back?”
“he explains very simply how all this works for images and some examples about the audio case.”
Simple 40 minute explanation of deep learning for images and audio.
brutuscat, 2012-06 · Strong recommendation · in “Microsoft Research make breakthrough in audio speech recognition”
“Check out this (awesome) talk”
Unsupervised feature learning outperforms hand-programmed models.
kevin1024, 2012-06 · Strong recommendation · in “Google & Stanford create a digital brain that learns to identify a human face”
“Here is a similar awesome by Andrew Ng”
FrojoS, 2012-08 · Strong recommendation · in “Brains, Sex and Machine Learning (Geoffrey Hinton at Google Tech Talks)”
“the one overview I've found the most useful is”
Most useful overview of unsupervised feature learning.
pilooch, 2012-11 · Strong recommendation · in “Scientists See Promise in Deep-Learning Programs”
“Andrew Ng has a fantastic example of visualizing deep belief nets”
Visualizes hierarchy of features learned by successive deep net layers.
michael_nielsen, 2013-04 · Strong recommendation · in “Neural Network Visualisation in Clojure”
“Here is a more in-depth presentation he gave on the same subject at a Google Tech Talk”
More in-depth presentation by Andrew Ng on the same subject.
colincsl, 2011-06 · Recommendation · in “Andrew Ng: Machine Learning in Robotics”
“Here's a video talking about current research into this at Stanford”
Current Stanford research on automatic feature learning.
dave_sullivan, 2011-11 · Recommendation · in “Stanford computer diagnoses breast cancer more accurately than human doctor”
Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.
Topics: deep learning, andrew ng, neural networks, feature learning, computer vision
Also recommended by the same people
talkBrains, Sex, and Machine LearningGoogle TechTalks · 7 HN recommenders · 2012–2017
lectureMIT's Pathway to Fusion Energy (IAP 2017) - Zach HartwigMIT Plasma Science and Fusion Center · 16 HN recommenders · 2017–2023
explainerTransformers, the tech behind LLMs | Deep Learning Chapter 53Blue1Brown · 13 HN recommenders · 2024–2026
podcastWhat Alcohol Does to Your Body, Brain & HealthAndrew Huberman · 7 HN recommenders · 2022–2023
lectureThe spelled-out intro to neural networks and backpropagation: building microgradAndrej Karpathy · 17 HN recommenders · 2022–2025
explainerBut what is a neural network? | Deep learning chapter 13Blue1Brown · 16 HN recommenders · 2017–2025
documentaryAlphaGo - The Movie | Full award-winning documentaryGoogle DeepMind · 10 HN recommenders · 2020–2025
talkUSENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?USENIX · 10 HN recommenders · 2018–2026