lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

small update on neural networks

Browse Source
This commit is contained in:
mhjensen
2018-10-16 13:54:54 +02:00
parent ce0c90eccd
commit 9bdb28895e
75 changed files with 6318 additions and 5703 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/NeuralNet/html/._NeuralNet-bs042.html
+128 -82
View File
@@ -92,54 +92,55 @@ Automatically generated HTML file from DocOnce source
'___sec30'),
('Defining the cost function', 2, None, '___sec31'),
('Example: binary classification problem', 2, None, '___sec32'),
('The Softmax function', 2, None, '___sec33'),
('Developing a code for doing neural networks with back '
'propagation',
2,
None,
'___sec33'),
('Collect and pre-process data', 2, None, '___sec34'),
('Train and test datasets', 2, None, '___sec35'),
('Define model and architecture', 2, None, '___sec36'),
('Layers', 2, None, '___sec37'),
('Weights and biases', 2, None, '___sec38'),
('Feed-forward pass', 2, None, '___sec39'),
('Matrix multiplications', 2, None, '___sec40'),
('Choose cost function and optimizer', 2, None, '___sec41'),
('Optimizing the cost function', 2, None, '___sec42'),
('Regularization', 2, None, '___sec43'),
('Matrix multiplication', 2, None, '___sec44'),
('Improving performance', 2, None, '___sec45'),
('Full object-oriented implementation', 2, None, '___sec46'),
('Evaluate model performance on test data', 2, None, '___sec47'),
('Adjust hyperparameters', 2, None, '___sec48'),
('Visualization', 2, None, '___sec49'),
('scikit-learn implementation', 2, None, '___sec50'),
('Visualization', 2, None, '___sec51'),
'___sec34'),
('Collect and pre-process data', 2, None, '___sec35'),
('Train and test datasets', 2, None, '___sec36'),
('Define model and architecture', 2, None, '___sec37'),
('Layers', 2, None, '___sec38'),
('Weights and biases', 2, None, '___sec39'),
('Feed-forward pass', 2, None, '___sec40'),
('Matrix multiplications', 2, None, '___sec41'),
('Choose cost function and optimizer', 2, None, '___sec42'),
('Optimizing the cost function', 2, None, '___sec43'),
('Regularization', 2, None, '___sec44'),
('Matrix multiplication', 2, None, '___sec45'),
('Improving performance', 2, None, '___sec46'),
('Full object-oriented implementation', 2, None, '___sec47'),
('Evaluate model performance on test data', 2, None, '___sec48'),
('Adjust hyperparameters', 2, None, '___sec49'),
('Visualization', 2, None, '___sec50'),
('scikit-learn implementation', 2, None, '___sec51'),
('Visualization', 2, None, '___sec52'),
('Building neural networks in Tensorflow and Keras',
2,
None,
'___sec52'),
('Tensorflow', 2, None, '___sec53'),
('Collect and pre-process data', 2, None, '___sec54'),
('Using TensorFlow backend', 2, None, '___sec55'),
('Optimizing and using gradient descent', 2, None, '___sec56'),
('Using Keras', 2, None, '___sec57'),
('Which activation function should I use?', 2, None, '___sec58'),
'___sec53'),
('Tensorflow', 2, None, '___sec54'),
('Collect and pre-process data', 2, None, '___sec55'),
('Using TensorFlow backend', 2, None, '___sec56'),
('Optimizing and using gradient descent', 2, None, '___sec57'),
('Using Keras', 2, None, '___sec58'),
('Which activation function should I use?', 2, None, '___sec59'),
('Is the Logistic activation function (Sigmoid) our choice?',
2,
None,
'___sec59'),
('The derivative of the Logistic funtion', 2, None, '___sec60'),
('The RELU function family', 2, None, '___sec61'),
('Which activation function should we use?', 2, None, '___sec62'),
'___sec60'),
('The derivative of the Logistic funtion', 2, None, '___sec61'),
('The RELU function family', 2, None, '___sec62'),
('Which activation function should we use?', 2, None, '___sec63'),
('A top-down perspective on Neural networks',
2,
None,
'___sec63'),
'___sec64'),
('Limitations of supervised learning with deep networks',
2,
None,
'___sec64')]}
'___sec65')]}
end of tocinfo -->
<body>
@@ -210,38 +211,39 @@ MathJax.Hub.Config({
<!-- navigation toc: --> <li><a href="._NeuralNet-bs031.html#___sec30" style="font-size: 80%;"><b>Setting up a Multi-layer perceptron model for classification</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs032.html#___sec31" style="font-size: 80%;"><b>Defining the cost function</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs033.html#___sec32" style="font-size: 80%;"><b>Example: binary classification problem</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs034.html#___sec33" style="font-size: 80%;"><b>Developing a code for doing neural networks with back propagation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs035.html#___sec34" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs036.html#___sec35" style="font-size: 80%;"><b>Train and test datasets</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs037.html#___sec36" style="font-size: 80%;"><b>Define model and architecture</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs038.html#___sec37" style="font-size: 80%;"><b>Layers</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs039.html#___sec38" style="font-size: 80%;"><b>Weights and biases</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs040.html#___sec39" style="font-size: 80%;"><b>Feed-forward pass</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs041.html#___sec40" style="font-size: 80%;"><b>Matrix multiplications</b></a></li>
<!-- navigation toc: --> <li><a href="#___sec41" style="font-size: 80%;"><b>Choose cost function and optimizer</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs043.html#___sec42" style="font-size: 80%;"><b>Optimizing the cost function</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs044.html#___sec43" style="font-size: 80%;"><b>Regularization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs045.html#___sec44" style="font-size: 80%;"><b>Matrix multiplication</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs046.html#___sec45" style="font-size: 80%;"><b>Improving performance</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs047.html#___sec46" style="font-size: 80%;"><b>Full object-oriented implementation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs048.html#___sec47" style="font-size: 80%;"><b>Evaluate model performance on test data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs049.html#___sec48" style="font-size: 80%;"><b>Adjust hyperparameters</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs050.html#___sec49" style="font-size: 80%;"><b>Visualization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs051.html#___sec50" style="font-size: 80%;"><b>scikit-learn implementation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs052.html#___sec51" style="font-size: 80%;"><b>Visualization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs053.html#___sec52" style="font-size: 80%;"><b>Building neural networks in Tensorflow and Keras</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs054.html#___sec53" style="font-size: 80%;"><b>Tensorflow</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs055.html#___sec54" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs056.html#___sec55" style="font-size: 80%;"><b>Using TensorFlow backend</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs057.html#___sec56" style="font-size: 80%;"><b>Optimizing and using gradient descent</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs058.html#___sec57" style="font-size: 80%;"><b>Using Keras</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs059.html#___sec58" style="font-size: 80%;"><b>Which activation function should I use?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs060.html#___sec59" style="font-size: 80%;"><b>Is the Logistic activation function (Sigmoid) our choice?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs061.html#___sec60" style="font-size: 80%;"><b>The derivative of the Logistic funtion</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs062.html#___sec61" style="font-size: 80%;"><b>The RELU function family</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs063.html#___sec62" style="font-size: 80%;"><b>Which activation function should we use?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs064.html#___sec63" style="font-size: 80%;"><b>A top-down perspective on Neural networks</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs065.html#___sec64" style="font-size: 80%;"><b>Limitations of supervised learning with deep networks</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs034.html#___sec33" style="font-size: 80%;"><b>The Softmax function</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs035.html#___sec34" style="font-size: 80%;"><b>Developing a code for doing neural networks with back propagation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs036.html#___sec35" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs037.html#___sec36" style="font-size: 80%;"><b>Train and test datasets</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs038.html#___sec37" style="font-size: 80%;"><b>Define model and architecture</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs039.html#___sec38" style="font-size: 80%;"><b>Layers</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs040.html#___sec39" style="font-size: 80%;"><b>Weights and biases</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs041.html#___sec40" style="font-size: 80%;"><b>Feed-forward pass</b></a></li>
<!-- navigation toc: --> <li><a href="#___sec41" style="font-size: 80%;"><b>Matrix multiplications</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs043.html#___sec42" style="font-size: 80%;"><b>Choose cost function and optimizer</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs044.html#___sec43" style="font-size: 80%;"><b>Optimizing the cost function</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs045.html#___sec44" style="font-size: 80%;"><b>Regularization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs046.html#___sec45" style="font-size: 80%;"><b>Matrix multiplication</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs047.html#___sec46" style="font-size: 80%;"><b>Improving performance</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs048.html#___sec47" style="font-size: 80%;"><b>Full object-oriented implementation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs049.html#___sec48" style="font-size: 80%;"><b>Evaluate model performance on test data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs050.html#___sec49" style="font-size: 80%;"><b>Adjust hyperparameters</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs051.html#___sec50" style="font-size: 80%;"><b>Visualization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs052.html#___sec51" style="font-size: 80%;"><b>scikit-learn implementation</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs053.html#___sec52" style="font-size: 80%;"><b>Visualization</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs054.html#___sec53" style="font-size: 80%;"><b>Building neural networks in Tensorflow and Keras</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs055.html#___sec54" style="font-size: 80%;"><b>Tensorflow</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs056.html#___sec55" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs057.html#___sec56" style="font-size: 80%;"><b>Using TensorFlow backend</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs058.html#___sec57" style="font-size: 80%;"><b>Optimizing and using gradient descent</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs059.html#___sec58" style="font-size: 80%;"><b>Using Keras</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs060.html#___sec59" style="font-size: 80%;"><b>Which activation function should I use?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs061.html#___sec60" style="font-size: 80%;"><b>Is the Logistic activation function (Sigmoid) our choice?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs062.html#___sec61" style="font-size: 80%;"><b>The derivative of the Logistic funtion</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs063.html#___sec62" style="font-size: 80%;"><b>The RELU function family</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs064.html#___sec63" style="font-size: 80%;"><b>Which activation function should we use?</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs065.html#___sec64" style="font-size: 80%;"><b>A top-down perspective on Neural networks</b></a></li>
<!-- navigation toc: --> <li><a href="._NeuralNet-bs066.html#___sec65" style="font-size: 80%;"><b>Limitations of supervised learning with deep networks</b></a></li>
</ul>
</li>
@@ -255,36 +257,80 @@ MathJax.Hub.Config({
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
<a name="part0042"></a>
<!-- !split -->
<!-- !split -->
<h2 id="___sec41" class="anchor">Choose cost function and optimizer </h2>
<h2 id="___sec41" class="anchor">Matrix multiplications </h2>
<p>
To measure how well our neural network is doing we need to introduce a cost function.
We will call the function that gives the error of a single sample output the <em>loss</em> function, and the function
that gives the total error of our network across all samples the <em>cost</em> function.
A typical choice for multiclass classification is the <em>cross-entropy</em> loss, also known as the negative log likelihood.
Since our data has the dimensions \( X = (n_{inputs}, n_{features}) \) and our weights to the hidden
layer have the dimensions
\( W_{hidden} = (n_{features}, n_{hidden}) \),
we can easily feed the network all our training data in one go by taking the matrix product
$$ X W^{h} = (n_{inputs}, n_{hidden}),$$
<p>
In <em>multiclass</em> classification it is common to treat each integer label as a so called <em>one-hot</em> vector:
and obtain a matrix that holds the weighted sum of inputs to the hidden layer
for each input image and each hidden neuron.
We also add the bias to obtain a matrix of weighted sums to the hidden layer \( Z^{h} \):
$$ y = 5 \quad \rightarrow \quad \hat{y} = (0, 0, 0, 0, 0, 1, 0, 0, 0, 0) ,$$
$$ y = 1 \quad \rightarrow \quad \hat{y} = (0, 1, 0, 0, 0, 0, 0, 0, 0, 0) ,$$
$$ \hat{z}^{l} = \hat{X} \hat{W}^{l} + \hat{b}^{l} ,$$
<p>
i.e. a binary bit string of length \( C \), where \( C = 10 \) is the number of classes in the MNIST dataset.
meaning the same bias (1D array with size equal number of hidden neurons) is added to each input image.
This is then passed through the activation:
$$ \hat{a}^{l} = f(\hat{z}^l) .$$
<p>
Let \( y_{ic} \) denote the \( c \)-th component of the \( i \)-th one-hot vector.
We define the cost function \( \mathcal{C} \) as a sum over the cross-entropy loss for each point \( \hat{x}_i \) in the dataset.
This is fed to the output layer:
$$ \hat{z}^{L} = \hat{a}^{L} \hat{W}^{L} + \hat{b}^{L} .$$
<p>
In the one-hot representation only one of the terms in the loss function is non-zero, namely the
probability of the correct category \( c' \)
(i.e. the category \( c' \) such that \( y_{ic'} = 1 \)). This means that the cross entropy loss only punishes you for how wrong
you got the correct label. The probability of category \( c \) is given by the softmax function. The vector \( \hat{\theta} \) represents the parameters of our network, i.e. all the weights and biases.
Finally we receive our output values for each image and each category by passing it through the softmax function:
$$ output = softmax (\hat{z}^{L}) = (n_{inputs}, n_{categories}) .$$
<p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># setup the feed-forward pass, subscript h = hidden layer</span>
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">sigmoid</span>(x):
<span style="color: #008000; font-weight: bold">return</span> <span style="color: #666666">1/</span>(<span style="color: #666666">1</span> <span style="color: #666666">+</span> np<span style="color: #666666">.</span>exp(<span style="color: #666666">-</span>x))
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">feed_forward</span>(X):
<span style="color: #408080; font-style: italic"># weighted sum of inputs to the hidden layer</span>
z_h <span style="color: #666666">=</span> np<span style="color: #666666">.</span>matmul(X, hidden_weights) <span style="color: #666666">+</span> hidden_bias
<span style="color: #408080; font-style: italic"># activation in the hidden layer</span>
a_h <span style="color: #666666">=</span> sigmoid(z_h)
<span style="color: #408080; font-style: italic"># weighted sum of inputs to the output layer</span>
z_o <span style="color: #666666">=</span> np<span style="color: #666666">.</span>matmul(a_h, output_weights) <span style="color: #666666">+</span> output_bias
<span style="color: #408080; font-style: italic"># softmax output</span>
<span style="color: #408080; font-style: italic"># axis 0 holds each input and axis 1 the probabilities of each category</span>
exp_term <span style="color: #666666">=</span> np<span style="color: #666666">.</span>exp(z_o)
probabilities <span style="color: #666666">=</span> exp_term <span style="color: #666666">/</span> np<span style="color: #666666">.</span>sum(exp_term, axis<span style="color: #666666">=1</span>, keepdims<span style="color: #666666">=</span><span style="color: #008000">True</span>)
<span style="color: #008000; font-weight: bold">return</span> probabilities
probabilities <span style="color: #666666">=</span> feed_forward(X_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;probabilities = (n_inputs, n_categories) = &quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(probabilities<span style="color: #666666">.</span>shape))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;probability that image 0 is in category 0,1,2,...,9 = </span><span style="color: #BB6622; font-weight: bold">\n</span><span style="color: #BA2121">&quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(probabilities[<span style="color: #666666">0</span>]))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;probabilities sum up to: &quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(probabilities[<span style="color: #666666">0</span>]<span style="color: #666666">.</span>sum()))
<span style="color: #008000; font-weight: bold">print</span>()
<span style="color: #408080; font-style: italic"># we obtain a prediction by taking the class with the highest likelihood</span>
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">predict</span>(X):
probabilities <span style="color: #666666">=</span> feed_forward(X)
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>argmax(probabilities, axis<span style="color: #666666">=1</span>)
predictions <span style="color: #666666">=</span> predict(X_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;predictions = (n_inputs) = &quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(predictions<span style="color: #666666">.</span>shape))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;prediction for image 0: &quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(predictions[<span style="color: #666666">0</span>]))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;correct label for image 0: &quot;</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(Y_train[<span style="color: #666666">0</span>]))
</pre></div>
<p>
<p>
<!-- navigation buttons at the bottom of the page -->
@@ -311,7 +357,7 @@ you got the correct label. The probability of category \( c \) is given by the s
<li><a href="._NeuralNet-bs050.html">51</a></li>
<li><a href="._NeuralNet-bs051.html">52</a></li>
<li><a href="">...</a></li>
<li><a href="._NeuralNet-bs065.html">66</a></li>
<li><a href="._NeuralNet-bs066.html">67</a></li>
<li><a href="._NeuralNet-bs043.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->