chore(README): simple neural network

This commit is contained in:
Mahdi Dibaiee 2016-09-10 01:20:08 +04:30
parent 58851611dc
commit 6cb130b15e

View File

@ -5,8 +5,45 @@ A simple Machine Learning library.
notMNIST dataset, cross-entropy loss, learning rate decay and sgd: notMNIST dataset, cross-entropy loss, learning rate decay and sgd:
![notMNIST](https://github.com/mdibaiee/sibe/blob/master/notmnist.png?raw=true) ![notMNIST](https://github.com/mdibaiee/sibe/blob/master/notmnist.png?raw=true)
See examples: ## Simple neural network
```haskell
let a = (sigmoid, sigmoid') -- activation function
-- random network, seed 0, values between -1 and 1,
-- two inputs, two nodes in hidden layer and a single output
rnetwork = randomNetwork 0 (-1, 1) 2 [(2, a)] (1, a)
-- inputs and labels
inputs = [vector [0, 1], vector [1, 0], vector [1, 1], vector [0, 0]]
labels = [vector [1], vector [1], vector [0], vector [0]]
-- define the session which includes parameters
session = def { network = rnetwork
, learningRate = 0.5
, epochs = 1000
, training = zip inputs labels
, test = zip inputs labels
} :: Session
initialCost = crossEntropy session
-- run gradient descent
-- you can also use `sgd`, see the notmnist example
newsession <- run gd session
let results = map (`forward` newsession) inputs
rounded = map (map round . toList) results
cost = crossEntropy newsession
putStrLn $ "- initial cost (cross-entropy): " ++ show initialCost
putStrLn $ "- actual result: " ++ show results
putStrLn $ "- rounded result: " ++ show rounded
putStrLn $ "- cost (cross-entropy): " ++ show cost
``` ```
## Examples
```bash
# neural network examples # neural network examples
stack exec example-xor stack exec example-xor
stack exec example-424 stack exec example-424