Share several links to neural computing and htm

Source: Internet
Author: User

I have been in Singapore for more than a month. I am currently working in the social robotics lab at the National University of Singapore. The lab is affiliated with ECE and idmi, and people are affiliated with NUS Graduate School for integrative science and engineering, yi _^, School of tobacco, liquor, and alcohol, agricultural industry and commerce)

Recently, I am mainly interested in visual cortex model and bio-converted red vision. I have read many things in this area and found some good links. So I 'd like to share them with you, at the same time, make a memo for yourself :)


There are two good articles about visual cortex and computational neuroscience, mr. Thursday @ mmdays:

1. The overall arrangement of visual transfer paths mainly describes the entire path from retina to the middle and high visual cortex of the brain, which is quite good and easy to understand. This is the fourth article in this series. The first three articles can be found at the relevant links at the end of the article. If you are interested in visual cortex, you can take a look.


2. the synchronization of flat learning and neural networks mainly introduces several main models of computational neurology in recent years, which are relatively comprehensive and enlightening. In particular, I am very interested in the last polychronous model, and I have open source code provided by the author on the Internet. If you are interested, try again.
In addition, there are good materials for this.
Neuroscience for Kids (Chinese version of "Little neuroscience" here), the author is quite loving and belongs to the neural science's first books; eye, brain and vision and the comptational brain, I personally think the illustration of the former is good, and the latter is easier to read; and the neural computation online course of Berkeley Redwood Institute of neuroscience

Bio-converted red vision, the information is relatively uneven, and a recent article about visual attention survey is not bad.


About htm (hierarchical temporal memory), it was recently discovered that numenta originally provided a complete Python & C ++ plugin & visual interface development chain:


1. Python: http://www.numenta.com/software-overview/software.php, documentation:Getting Started Guide(PDF),Programmer's Guide(PDF)
2. c ++ Plugin: It looks like a website update. the download is removed by numenta and will be uploaded to csdn tomorrow. The document is as follows:Plugin developer's Guide
3. Develop the vitamin D toolkit on the visual interface. The document is within the installation package.

In addition, there is a neocortex project based on the HTM principle on SourceForge, which is a C ++ project using qt gui and is quite good. You can download it and run it.


If you are not familiar with htm, you can take a look at Jeff Hawkins's on Intelligence (Chinese Translation: creative wisdom, here are the key summaries of the book) and Dileep George's PhD thesis: how the brain might work is used to understand the theoretical basis and algorithm principle of HTM.

The numenta website also provides links to a large number of reference knowledge, including a large number of online resources related to statistics learning, neuroscience, and machine learning, which are recommended.


For the latest HTM progress, let's take a look at Jeff Hawkins's speech in UBC, which mentioned an improved algorithm FDR for htm. On the numenta Forum, some enthusiastic netizens tried to write a FDR Matlab code.

Recently I am studying Python and trying to build my own HTM network. If you are interested, you can try it. I hope you can have more discussions here.


Also recommend a good blog: http://www.andol.info/research look at it to know

 

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.