update content

README.md

@@ -15,67 +15,60 @@ var output = network.activate(input);
 
 ## Performance
 
-### [MNIST](https://yann.lecun.com/exdb/mnist/)
-
-* **MLP specification**
- * **Neurons**
- * ```400``` input
- * ```40``` hidden
- * ```4``` output
- * **Learning rate**
- * ```0.1```
- * **Training set**
- * **Size**
- * ```59999``` digits
- * **Testing set**
- * **Size**
- * ```9999``` digits
+### [MNIST [0-9]](https://yann.lecun.com/exdb/mnist/)
+
+* **Neurons**
+ * ```400``` input
+ * ```40``` hidden
+ * ```4``` output
+* **Learning rate**
+ * ```0.1```
+* **Training set**
+ * ```59999``` digits
+* **Testing set**
+ * ```9999``` digits
 * **Measured success rate**
  * ```82.08820882088209%```
 
-### ```abcdefghijklmnopqrstuvwxyz```
+### [a-z]
 
 * **Fonts**
  * sans-serif
  * serif
-* **MLP specification**
- * **Neurons**
- * ```400``` input
- * ```40``` hidden
- * ```8``` output
- * **Learning rate**
- * ```0.1```
- * **Training set**
- * **Size**
- * ```52000``` characters
- * **Sample**
- * ![abcdefghijklmnopqrstuvwxyz](https://raw.github.com/mateogianolio/mlp-character-recognition/master/examples/abcdefghijklmnopqrstuvwxyz.png)
- * **Testing set**
- * **Size**
- * ```13000``` characters
+* **Neurons**
+ * ```400``` input
+ * ```40``` hidden
+ * ```8``` output
+* **Learning rate**
+ * ```0.1```
+* **Training set**
+ * ```52000``` characters
+ * **Sample**
+ * ![abcdefghijklmnopqrstuvwxyz](https://raw.github.com/mateogianolio/mlp-character-recognition/master/examples/abcdefghijklmnopqrstuvwxyz.png)
+* **Testing set**
+ * ```13000``` characters
 * **Measured success rate**
  * ```96.32307692307693%```
 
-### ```0123456789```
+### [0-9]
 
 * **Fonts**
  * sans-serif
  * serif
-* **MLP specification**
- * **Neurons**
- * ```400``` input
- * ```40``` hidden
- * ```8``` output
- * **Learning rate**
- * ```0.1```
- * **Training set**
- * **Size**
- * ```20000``` characters
- * **Sample**
- * ![0123456789](https://raw.github.com/mateogianolio/mlp-character-recognition/master/examples/0123456789.png)
- * **Testing set**
- * **Size**
- * ```5000``` characters
+* **Neurons**
+ * ```400``` input
+ * ```40``` hidden
+ * ```8``` output
+* **Learning rate**
+ * ```0.1```
+* **Training set**
+ * **Size**
+ * ```20000``` characters
+ * **Sample**
+ * ![0123456789](https://raw.github.com/mateogianolio/mlp-character-recognition/master/examples/0123456789.png)
+* **Testing set**
+ * **Size**
+ * ```5000``` characters
 * **Measured success rate**
  * ```99.22%```
 
@@ -139,24 +132,68 @@ $ node main.js
 
 ## Example
 
-Here is an example run of the script:
+Here is an example run of the script (with ```mnist``` set to true in ```config.json```):
 
 ```bash
 $ node main.js
 reading config file ...
 ... done
 
-generating images ...
+parsing MNIST data ...
+digit 6 from training set
+00000000000000000000
+00000001111000000000
+00000011110000000000
+00000011100000000000
+00000111000000000000
+00000111000000000000
+00001110000000000000
+00001110000000000000
+00001110000000000000
+00001100000001110000
+00011100000111110000
+00011100001111111000
+00011100001110111000
+00011100011100111000
+00001110111000111000
+00001111111001110000
+00000111111111110000
+00000011111111000000
+00000001111110000000
+00000000000000000000
+
+digit 8 from testing set
+00000000000000000000
+00000000111110000000
+00000001111111110000
+00000011110011111100
+00000011100000111100
+00000011100000011100
+00000011100000111100
+00000001100001111000
+00000001111111110000
+00000011111111100000
+00001111111110000000
+00001111111100000000
+00011100111100000000
+00011000111100000000
+00111000011000000000
+00111000011000000000
+00111000011000000000
+00011100011000000000
+00011100111000000000
+00001111110000000000
+
 ... done
 
 neural network specs:
  layers:
  input: 400 neurons.
  hidden: 40 neurons.
- output: 8 neurons.
+ output: 4 neurons.
  learning rate: 0.1
- training set: 20000 characters.
- testing set: 5000 characters.
+ training set: 59999 characters.
+ testing set: 999 characters.
 
 learning ...
 progress: 10%
@@ -172,7 +209,7 @@ progress: 90%
 
 network saved to ./network.js
 
-testing on 5000 samples ...
+testing on 999 samples ...
 progress: 10%
 progress: 20%
 progress: 30%
@@ -184,9 +221,5 @@ progress: 80%
 progress: 90%
 ... done
 
-success rate: 99.58 %
-```
-
-## Contribute
-
-Feel free to fork and submit pull requests.
+success rate: 81.38138138138137 %
+```