Difference between revisions of "Connectionism, neural nets"

From Helpful
Jump to: navigation, search
m (Connectionism)
m
Line 150: Line 150:
 
This makes it a more generic version of the MP neuron and perceptron, which can do their work with a few thresholds at the input and output layer.
 
This makes it a more generic version of the MP neuron and perceptron, which can do their work with a few thresholds at the input and output layer.
  
 +
https://towardsdatascience.com/mcculloch-pitts-model-5fdf65ac5dd1
  
 +
https://towardsdatascience.com/perceptron-learning-algorithm-d5db0deab975
  
 
They  
 
They  
Line 272: Line 274:
  
 
* R-CNN (Region-based Convolutional Neural Networks)
 
* R-CNN (Region-based Convolutional Neural Networks)
 +
 +
 +
https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-convolutional-neural-networks
  
 
-->
 
-->

Revision as of 21:28, 8 July 2020

This is more for overview of my own than for teaching or exercise.

Overview of the areas

Arithmetic · 'elementary mathematics' and similar concepts
Set theory, Category theory
Geometry and its relatives · Topology
Elementary algebra - Linear algebra - Abstract algebra
Calculus and analysis
Logic
Semi-sorted
 : Information theory · Number theory · Decision theory, game theory · Recreational mathematics · Dynamical systems · Unsorted or hard to sort


Math on data:

  • Statistics as a field
some introduction · areas of statistics
types of data · on random variables, distributions
Virtues and shortcomings of...
on sampling · probability
glossary · references, unsorted
Footnotes on various analyses

Other data analysis, data summarization, learning

Regression · Classification, clustering, decisions · dimensionality reduction · Optimization theory, control theory
Connectionism, neural nets · Evolutionary computing




Connectionism is the idea that interesting things are emergent effects from interconnected networks of simple units.

The term is used in cognitive psychology, cognitive science, neuroscience, and philosophy of mind, to model mental and behavioral phenomena -- but most recognizably in artificial intelligence in the form of neural networks.

Another angle is computationalism, which works more on higher-level expression, and tends to think connectionism is no more than lower-level association. The two are not necessarily incompatible, but certainly distinct approaches.


Neural networks

This article/section is a stub — probably a pile of half-sorted notes, is not well-checked so may have incorrect bits. (Feel free to ignore, fix, or tell me)

Terminology old and new

ANN history

Perceptrons

Sigmoid neuron

Multilayer Perceptron (MLP)

A little fancier than perceptrons

MLP

RNNs

CNNs

Deep

Unsorted