Update to Rubix ML 0.3.0

LICENSE.md → LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 The Rubix ML Community
+Copyright (c) 2020 Rubix ML
 Copyright (c) 2020 Andrew DalPino
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

README.md

@@ -114,9 +114,9 @@ $scores = $estimator->scores();
 
 Then, we can plot the values using our favorite plotting software such as [Tableu](https://public.tableau.com/en-us/s/) or [Excel](https://products.office.com/en-us/excel-a). If all goes well, the value of the loss should go down as the value of the validation score goes up. Due to snapshotting, the epoch at which the validation score is highest and the loss is lowest is the point at which the values of the network parameters are taken for the final model. This prevents the network from overfitting the training data by effectively *unlearning* some of the noise in the dataset.
 
-![Cross Entropy Loss](https://raw.githubusercontent.com/RubixML/MNIST/master/docs/images/training-loss.svg?sanitize=true)
+![Cross Entropy Loss](https://raw.githubusercontent.com/RubixML/MNIST/master/docs/images/training-losses.png)
 
-![F1 Score](https://raw.githubusercontent.com/RubixML/MNIST/master/docs/images/validation-score.svg?sanitize=true)
+![F1 Score](https://raw.githubusercontent.com/RubixML/MNIST/master/docs/images/validation-scores.png)
 
 ### Saving
 We can save the trained network by calling the `save()` method provided by the [Persistent Model](https://docs.rubixml.com/en/latest/persistent-model.html) wrapper. The model will be saved in a compact serialized format such as the [Native](https://docs.rubixml.com/en/latest/persisters/serializers/native.html) PHP serialization format or [Igbinary](https://docs.rubixml.com/en/latest/persisters/serializers/igbinary.html).
@@ -317,4 +317,4 @@ Email: corinna 'at' google.com
 >- Y. LeCun et al. (1998). Gradient-based learning applied to document recognition.
 
 ## License
-The code is licensed [MIT](LICENSE.md) and the tutorial is licensed [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).
+The code is licensed [MIT](LICENSE) and the tutorial is licensed [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).

composer.json

@@ -3,7 +3,7 @@
     "type": "project",
     "description": "Handwritten digit recognizer using a feed forward neural network and the MNIST dataset of 70,000 human-labeled handwritten digits.",
     "homepage": "https://github.com/RubixML/MNIST",
-    "license": "Apache-2.0",
+    "license": "MIT",
     "keywords": [
         "classification", "cross validation", "dataset", "data science", "dropout", "example project",
         "feed forward", "image recognition", "image classification", "leaky relu", "machine learning",
@@ -13,18 +13,14 @@
     "authors": [
         {
             "name": "Andrew DalPino",
-            "email": "[email protected]",
-            "homepage": "https://andrewdalpino.com",
+            "homepage": "https://github.com/andrewdalpino",
             "role": "Lead Engineer"
         }
     ],
     "require": {
         "php": ">=7.2",
         "ext-gd": "*",
-        "rubix/ml": "^0.1.0"
-    },
-    "suggest": {
-        "ext-tensor": "For faster training and inference"
+        "rubix/ml": "^0.3.0"
     },
     "scripts": {
         "train": "@php train.php",