Deep Learning has benefited primarily and continues to do so thanks to the pioneering works of Geoff Hinton, Yann Lecun and Yoshua Bengio. Contributions of Yann Lecun, especially in developing convolutional neural networks and their applications in computer vision and other areas of artificial intelligence form the basis of many products and services deployed across most technology companies today.
Here are a few of Yann’s groundbreaking research papers that have contributed greatly to this field:
Back-propagation Applied to Handwritten Zip Code Recognition
Cited by: 5172 | Published in 1989
The ability of neural networks to generalize can be greatly enhanced by providing constraints from the task domain. As a follow up to his widely popular work on back-prop, in this paper, Yann and his peers demonstrate how such constraints can be integrated into a backpropagation network through the architecture of the network.
This approach has been successfully applied to the recognition of handwritten zip code digits provided by the US Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
Read the original paper here.
Generalization And Network Design Strategies
Cited by: 737 | Published in 1989
This paper demonstrates techniques to improve learning speed in networks for image recognition tasks and how these approaches can be extended to other applications such as speech recognition. The main point of this work is to show that good generalization performance can be obtained if some a priori knowledge about the task is built into the network.
Read the original paper here.
Convolutional Networks For Images, Speech, And Time Series
Cited by: 2578 | Published in 1995
In this seminal paper, Yann collaborated with Bengio to uncover the reach of CNNs. Today, many machine vision tasks are flooded with CNNs. They are the workhorses of autonomous driving vehicles and even screen locks on mobiles.
This work discusses the variants of CNNs addressing the innovations of Geoff Hinton while also indicating how easy it is to implement CNNs on hardware devices dedicated to image processing tasks.
Read the original paper here.
Gradient-based Learning Applied To Document Recognition
Cited by: 20831 | Published in 1998
The main message of this paper is that better pattern recognition systems can be built by relying more on automatic learning and less on hand-designed heuristics.
Yann Lecun along with fellow Turing award winner Yoshua Bengio, demonstrate that show that the traditional way of building recognition systems by manually integrating individually designed modules can be replaced by a well-principled design paradigm called Graph Transformer Networks that allows training all the modules to optimise a global performance criterion.
Read the original paper here.
Efficient Back-prop
Cited by: 2799 | Published in 1998
In this paper, Yann and his collaborators demonstrate why back-propagation works the way it works. In this 20-year-old research, the authors propose tricks to improve back-prop. This paper is significant now more than ever as there has been a sporadic rise in search of alternatives to back-prop. The techniques detailed in this work will navigate the reader through the foundations of neural networks and their shortcomings.
Read the original paper here.
Yann Lecun is currently the Chief AI Scientist for Facebook AI Research (FAIR) and also a Silver Professor at New York University on a part-time basis, mainly affiliated with the NYU Center for Data Science, and the Courant Institute of Mathematical Science.
Yann LeCun was one of the recipients of the 2018 ACM A.M. Turing Award for his contributions to conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing. He shares this award with his long-time collaborators Geoff Hinton and Yoshua Bengio.
Check out Yann’s other significant works here.
