Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

106062510_homework0 #38

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

106062510_homework0 #38

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 43 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,5 +4,47 @@ he/she can be a professor (e.g., Yann LeCun), a Ph.D student (e.g., Joseph Chet
To avoid writing the same person, please report the person's name in
https://docs.google.com/spreadsheets/d/153XruMO7DPONzBTkxh8ZoYSto1E_2zO021vs0prWZ_Q/edit?usp=sharing
First come first serve!

-------
Write here
## Yann LeCun


[Yann LeCun](yann.lecun.com) is a computer scientist mainly contributs in machine learning, computer vision, mobile robotics, and computational neuroscience. He's the dircetor of [Facebook AI research](https://research.fb.com/category/facebook-ai-research-fair/) and a professor at NYU.


Yann LeCun was born in France. He recieved a PhD in CS from Universite Pierre et Marie Curie where he proposed an early form of the back-propagation learning algorithm for nerual nets.


He joined Adaptive Systems Research Department at At&T Bell Laboratories in 1988. At there, he developed many new machine learning methods. He is well known for his works on CNN. He is the one who first applied backpropagation to cnn([Backpropagation Applied to Handwritten Zip Code](yann.lecun.com/exdb/publis/pdf/lecun-89e.pdf)) in 1989, which largely inspired later works on neural networks. Furthermoere, the propose of Lenet-5([Gradient-Based Learning Applied to Document Recognition](yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf), with Yoshua Bengio), which was a breakthrough in handwriting and OCR.


He joined At&T Labs-Research as head of Image Processing Research Department and worked on [DjVu](https://en.wikipedia.org/wiki/DjVu)(a computer file format using compression).


After that, he joined NTU in 2003, and became the director of facebook Fair in 2013.


In 2013, Yann LeCun co-founed the [ICLR](www.iclr.cc)(International Conference on Learning Representations) with Yoshua Bengio.

To sum up, Yann LeCun is a remarkable researcher on his research area. He proposed many inspiring works, and is still making contributions to ml, cv, and computational neurosciences.

Some of his representative papers is as follow:

* [Farabet et al. 2013](http://yann.lecun.com/exdb/publis/pdf/farabet-pami-13.pdf): Learning Hierarchical Features for Scene Labeling
* [Hadsell et al. 2009](http://yann.lecun.com/exdb/publis/pdf/hadsell-jfr-09.pdf): Learning Long-Range Vision for Autonomous Off-Road Driving
* [LeCun et al. 2006](yann.lecun.com/exdb/publis/pdf/lecun-06.pdf): A Tutorial on Energy-Based Learning
* [Bengio, LeCun 2007](http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf): Scaling Learning Algorithms Towards AI
* [Mirowski et al., 2008](http://yann.lecun.com/exdb/publis/pdf/mirowski-mlsp-08.pdf): Comparing SVM and Convolutional Networks for Epileptic Seizure Prediction from Intracranial EEG
* [Chopra et al., 2007](http://yann.lecun.com/exdb/publis/pdf/chopra-kdd-07.pdf): Discovering the hidden structure of house prices with non-parametric latent
* [LeCun, Huang, and Bottou, 2004](http://yann.lecun.com/exdb/publis/pdf/lecun-04.pdf): Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting
* [Osadchy, Miller and LeCun, 2007](http://rita.osadchy.net/papers/OsadchyLeCunJMLR.pdf): Synergistic Face Detection and Pose Estimation with Energy-Based Model
* [Hadsell, Chopra and LeCun, 2006](http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf): Dimensionality Reduction by Learning an Invariant Mapping
* [Chopra and Hadsell and LeCun, 2005](http://yann.lecun.com/exdb/publis/pdf/chopra-05.pdf): Learning a Similarity Metric Discriminatively, with Application to Face Verification
* [LeCun et al., 2005](http://yann.lecun.com/exdb/publis/pdf/lecun-dave-05.pdf): Off-Road Obstacle Avoidance through End-to-End Learning
* [LeCun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf): Gradient-Based Learning Applied to Document Recognition
* [LeCun et al., 1998](http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf): Efficient BackProp
* [Bottou et al., 1998](http://yann.lecun.com/exdb/publis/pdf/bottou-98.pdf): High Quality Document Image Compression with DjVu
* [LeCun, 1988](http://yann.lecun.com/exdb/publis/pdf/lecun-88.pdf): A theoretical framework for Back-Propagation
* [LeCun, Denker, and Solla, 1990](http://yann.lecun.com/exdb/publis/pdf/lecun-90b.pdf): Optimal Brain Damage
* [LeCun and Kanter and Solla, 1991](http://yann.lecun.com/exdb/publis/pdf/lecun-kanter-solla-91.pdf): Eigenvalues of covariance matrices: application to neural-network learning