Comments (8)
Related to issue #4.
from associative_memory.
I have found a reference to a model called "Brain-states-in-a-box" or "BSB" for short in paper #31. I have created an issue to review the paper that is referenced to this model, issue #32.
from associative_memory.
I have found a reference to a model called "Brain-states-in-a-box" or "BSB" for short in paper #31. I have created an issue to review the paper that is referenced to this model, issue #32.
Perfect! I'll add it to the list. If we have too many models, when we start to focus our research in a couple of weeks, we may select the most interesting from the list at that point.
from associative_memory.
Two more models listed by the same paper are:
Hamming network, issue #34
Boltzmann Machine, issue #33
from associative_memory.
I have not assigned any of those three new papers to anyone, so if anyone is interested go ahead and grab any of the issues :)
from associative_memory.
Transderivational search, used for resolving ambiguity and attaching semantical meaning to communication. Roughly corresponds to fuzzy search, which may be implemented using content-addressable memory.
As TDS is believed to play a fundamental part in making humans understand language, achieving fuzzy matching (or associative recall) may be crucial for future AI entities to gain an understanding of human language.
We still need to find a good paper explaining how the transderivational serach model for associative memory works. That is, if we deem this model relevant enough to go into depths to find out details about it.
from associative_memory.
Hopfields may be used for auto-associative memory recall (recalling a memory from a fraction or piece of the memory, i.e. fill in the missing details).
Bidirectional associative memory may be used for hetroassociative memory (recalling one category from another; e.g. the pattern for banana triggers the pattern for monkey to fire in the brain)
from associative_memory.
We ended up focusing on tree models (one each),
- Wenting: Hopfield Network
- Lucas: Boltzmann Machine
- Robin: Memory Resistor
Other models have been outlined in the description of this issue, and may be evaluated in the future. Closing this issue for now.
from associative_memory.
Related Issues (20)
- review: Yoshizawa, Shuji, Masahiko Morita, and Shun-Ichi Amari. "Capacity of associative memory using a nonmonotonic neuron model." Neural Networks 6.2 (1993): 167-176. HOT 1
- review: AHaH Computing–From Metastable Switches to Attractors to Machine Learning HOT 1
- report: Introduction
- report: Introduction, Aim and Objectives
- report: Introduction, Hebbian Learning
- report: Models of Associative Memory
- report: Models of Associative Memory, Hopfield Network
- report: Models of Associative Memory, Boltzmann Machine
- report: Models of Associative Memory, Memory Resistor
- report: Current Capabilities
- report: Current Capabilities, Hopfield Network
- report: Current Capabilities, Boltzmann Machine
- report: Current Capabilities, Memory Resistor
- report: Future Potential
- report: Future Potential, Intelligent Systems
- report: Future Potential, Energy Efficiency
- report: Conclusion
- report: Abstract
- review: Knowm
- review: Numenta, NuPIC
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from associative_memory.