JS Machine Learning Toolkit
Pet project of mine
to understand ML
Bringing the power of computer thought to the web.
Simple Hill Climbing
Hill climbing is a optimization technique used to find optimum values in large datasets. This technique can be applied to problems such as the travelling salesman issue.
Optima: 0
Iterations: 0
Bayes Predictions
Bayes theorem implementation that is used to calculate outputs given a set of inputs. This technique can be applied to making predictions such as choosing the winner of a football match.
Test data used are 10 fixtures between Manchester United and Manchester City. First game was on 8 Apr 2013, last game was 27 Apr 2017
Probability: 0
Output: 0
The correct outcome for the match was L for Manchester United. The outcome games was played 10 Dec 2017
Neural Networks
Neural networks can be trained to learn from a set of given inputs with their corresponsing outputs. As neural networks "learn" they see patterns that humans may not see.
The following example shows how a neural network can be trained to learn the outcomes of a XOR gate.
| Training Data | ||
|---|---|---|
| # | Inputs | Outputs |
| 1 | [0, 0] | 0 |
| 2 | [0, 1] | 1 |
| 3 | [1, 0] | 1 |
| 4 | [1, 1] | 0 |
These inputs are trained on a neural network and the results are as follows: