Difference between revisions of "Algorithms"
| Line 5: | Line 5: | ||
* [http://en.wikipedia.org/wiki/Outline_of_machine_learning Outline of machine learning | Wikipedia] | * [http://en.wikipedia.org/wiki/Outline_of_machine_learning Outline of machine learning | Wikipedia] | ||
* [http://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-choice How to choose algorithms for Microsoft Azure Machine Learning | Microsoft] | * [http://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-choice How to choose algorithms for Microsoft Azure Machine Learning | Microsoft] | ||
| + | * [http://www.arxiv-sanity.com/ Arxiv Sanity Preserver] to accelerate research | ||
<youtube>ggIk08PNcBo</youtube> | <youtube>ggIk08PNcBo</youtube> | ||
<youtube>nl_4WFHQ4LU</youtube> | <youtube>nl_4WFHQ4LU</youtube> | ||
<youtube>gzYFDNKHSMM</youtube> | <youtube>gzYFDNKHSMM</youtube> | ||
| + | <youtube>pQyzdwHBbqo</youtube> | ||
| + | <youtube>SHTOI0KtZnU</youtube> | ||
| + | |||
Architecture: | Architecture: | ||
Revision as of 06:23, 10 July 2018
- Hyperparameters
- A guide to machine learning algorithms and their applications
- Outline of machine learning | Wikipedia
- How to choose algorithms for Microsoft Azure Machine Learning | Microsoft
- Arxiv Sanity Preserver to accelerate research
Architecture:
- Variables type
- Variable scaling
- Cost function
- Type of neural network - CNN, RNN, FFN
- Number of layers, hidden
- Type of layers
- LSTM, Dense, Highway
- Convolutional
- Pooling
- Weight initialization type
- Number of nodes
- Type of activation function - linear, Sigmoid, ReLU
- Dropout rate (or not)
- Threshold
Neural Networks
