Notes on Convolutional Neural Networks

Yann Le Cun
CNN - Convolutional neural

Yann Le Cun was recently featured on NYAS’s Science and the City podcast. He spoke about visual processing using Artificial Neural Networks (ANNs) and in particular his work on the system that reads the amounts on your cheques at the ATM.  The host, Alana Range, notes that her ATM has never gotten her cheque amounts wrong. I myself no longer bother to check.

The technology behind the ATMs was developed by Le Cun and others almost 10 years ago, at AT&T Bell Labs [which, tragically, has been closed down]. The algorithm they developed [now] goes under the name LeNet, and is a multi-layer backpropagation Neural network called a Convolution Neural Network.  I will explain this terminology in my next post. [Update: explanation now posted.]

In the object recognition demonstration, Yann Le Cun describes four output interpretations in the LeNet algorithm: 1) edges and contours, 2) motifs, 3) categories, and finally 4) objects. By narrowing down options in several steps LeNet can arrive at the final outputn (identifying the object) far more rapidly — the demonstration on the podcast proceses 4-5 pictures each second, and can recognize five different objects.  There are also demonstrations online on Yann Le Cun’s website.

I wondered as I listened to this podcast about the comparisons drawn between mammalian visual processing and Le Cun’s algorithm. There were some very pronounced differences that suggest that our brains utilize a totally different technique, not simply a more complex version of LeNet, as was implied in the interview. These differences were:

Source: Alan's Mutterings

Springer Camera-Based Document Analysis and Recognition: 4th International Workshop, CBDAR 2011, Beijing, China, September 22, 2011, Revised Selected Papers ... Vision, Pattern Recognition, and Graphics)
Book (Springer)

You might also like:

Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
Lecture 04, part 4 | Pattern Recognition
Lecture 04, part 4 | Pattern Recognition
Neocognitron by MATLAB: Recognition Test
Neocognitron by MATLAB: Recognition Test

Your child is expected to be

2011-03-21 05:40:32 by dixiessmom

Supported by both parents. However, remember the other parent is supporting the child when she is there. They are feeding the child,paying for activities etc. Whether they have to provide any money to you depends on many factors.You should google the child support calculator for CA.I would first try to work out a parenting plan. If the child can only see the parent once a month,what can you offer in exchange? more time over the summer? extra school breaks? This is not a drastic change but be ready to make up for the lost time. Also, let the other parent know that any time they want to come to CA they are welcome and can go to the activities with the child

Treatment that gets on your nerves  — Irish Times
Your body contains a complex network of nerves, which are like electrical information highways, that plays an important role in how you sense the environment – and pain – and how and when parts of your body move. ... Funded through Science Foundation ...


Related posts:

  1. What is Convolutional Neural Networks?
  2. Logistic function Neural Networks
  3. Learning and Evolution in neural networks