Temporal Memory in Racket [DEMO #8]
3 views
Formal Metadata
Title 
Temporal Memory in Racket [DEMO #8]

Title of Series  
Number of Parts 
19

Author 

License 
CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. 
Identifiers 

Publisher 
Numenta Platform for Intelligent Computing (NuPIC)

Release Date 
2014

Language 
English

Content Metadata
Subject Area  
Abstract 
A Racketbased implementation of the current temporal memory algorithm.

00:00
Point (geometry)
Programming paradigm
Computer programming
Implementation
Presentation of a group
Code
Multiplication sign
Scientific modelling
1 (number)
Student's ttest
Mereology
Field (computer science)
Theory
Frequency
Programmer (hardware)
Mathematics
Iteration
Natural number
Energy level
Data structure
Recursion
Subtraction
Social class
Area
Programming language
Standard deviation
Process (computing)
Information
Mapping
Software developer
Moment (mathematics)
Electronic mailing list
Sampling (statistics)
Instance (computer science)
Functional (mathematics)
Word
Arithmetic mean
Integrated development environment
Function (mathematics)
output
Natural language
Right angle
Quicksort
Uniform space
Hacker (term)
Data type
Data structure
04:47
Area
Metropolitan area network
Rule of inference
User interface
Mapping
Computer
Variety (linguistics)
Multiplication sign
Moment (mathematics)
Open source
Functional (mathematics)
Bulletin board system
Summation
Prediction
Function (mathematics)
Hill differential equation
Quicksort
Units of measurement
Subtraction
Social class
05:44
Order (biology)
Texture mapping
Augmented reality
Electric current
05:59
Texture mapping
Open source
Color management
Functional (mathematics)
Computer
Emulation
Maxima and minima
Number
Mathematics
Function (mathematics)
Statistics
Bounded variation
Error message
Form (programming)
Physical system
06:19
Metropolitan area network
Computer programming
System call
State of matter
Temporal logic
Scientific modelling
Simultaneous localization and mapping
Demo (music)
1 (number)
Bit
Functional (mathematics)
Duality (mathematics)
Readonly memory
Function (mathematics)
Universe (mathematics)
Normal (geometry)
output
Recursion
Form (programming)
Physical system
00:00
Europe wherever there are upset stomach as an excuse asked start to make use of it in the development of the year so what I'm essentially goes on how 1 might implement new sample and all of the change in the in and all that so the reason that this is actually something that was really good understanding of how the people that we were really like the and the other than those in region in the field of this part of is also 1 of the other thing is you have to think about the following list of General I wanted to do something that was functional and essentially held at the moment in time what your input on use of inputs directly to essentially is all about purely transforming information contained in from the and that was really interesting the and what have we got about what the so this is really going to be 1 of the of the of the nature of the process so that was not issue of what you have in mind the reason for that is that is that the use of commercial and is the reason I kind of like that of the people that presentation which is also another the model of actually ranking is being used right now across many different middle schools and that was the 1st program in which I feel like a lot of students are getting into the sort of thing so this land area and I also think about solving our program program that were less than unity environments and so the motivation for the work programme words intelligence and so I've tried couple times but finally got the point where you know a few of the motivation to really sort of have a go at the time that the price of things and so this is the 1st of all we have access to that and I have a loud and minus hello world and I think that's the have best of the and so the only thing that I want to make sure that need amongst not only of the list and general all instances that there is a succinct and natural language very important to the community is very succinct between how we represent natural language and how we represent programming language so innocent and that everything can be thought of as a means of going to sort the and the idea is that over time and essentially you know that the goal of the program that essentially it's on how to program so it's essentially a revolving the code to the of and that so those are analyzed and now I want to just touch on some of the differences are between the implementation and working on genes the entire so there are not that many differences essentially wanted to make sure that the mapping of the closest possible but there are some slight deviations so 1st of you know Indian right to be there are no classes also mentioned foragers pure information moving from point a to point B so that's the 1st thing the other 1 is to have you functions and we are literally the recursion recursion is kind of the a level of the relationship with some people some people say this is what the theory is going through a period of time then just kind of goes along with the idea of a but you are really interesting things different types of workers techniques that are more along with you will you using that led to that and the other thing and what's loans this implementation working on is that I want 1 uniform data structure that's just what I want and the sort of thing you so I was with a list of lists because know this is actually short this process so you know it's just that was pretty good to me as well as in in this implementation learning is all the of that of the the of the time I think about the will of the people and many of you have probably noticed that since then the 3rd part of the challenge of so I don't normally show called for the provision of thinking just going through a couple of is the main function problem and that's a couple
04:51
of things show you what I mean by
04:54
sort of kind clarity in doing this mapping so for so this is the area is given your main computing functions for how we can only which is the exact same thing you given the same and that's about as a way to reduce so 1 of the main difference is that talked about in the middle class but also the way we can get rid of this you know what this is essentially at each moment in time to be being all the neurons and their associated sentiments and so this is obviously very long variety but you kind of know that anything I know where it is so what is the what want to work is all so sort of what that means is the other 1 is just kind of the the use of this book will about the final years of I just
05:45
kind of in the current neurons there used to be compute the active site of what you can find most of the
05:53
stuff from the initial use and is the last thing I want to point out that the
06:01
quality the of the following pretty much have to learn in system so
06:07
basically instead of weak base only at the realizations of the functions and the idea is that you just essentially as you know we were error here is the use of the natural variation of the computer
06:22
so basically recursion is just 1 of the 1st ones find a function you call that same function function so what we're doing is we're essentially not worried about the state of the program at all and the only thing that we actually out what this 1 goes off into the consulate classifier so the norm of the and the rest of the the outputs and stay within the university of system and only we only need to with actually and you know it has to be the form from using so this this is how you can to use so all you so of the you from think the you will you you you think of the the will of the people of UK expected to do there is still a directed 1st of all I just want to say that there is a little bit of the such models and I'm a bit of a