small update on neural networks
This commit is contained in:
mhjensen
@@ -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="._NeuralNet-bs042.html#___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="#___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="._NeuralNet-bs042.html#___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="#___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>
|
||||
@@ -257,23 +259,117 @@ MathJax.Hub.Config({
|
||||
<a name="part0046"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec45" class="anchor">Improving performance </h2>
|
||||
<h2 id="___sec45" class="anchor">Matrix multiplication </h2>
|
||||
|
||||
<p>
|
||||
As we can see the network does not seem to be learning at all. It seems to be just guessing the label for each image.
|
||||
In order to obtain a network that does something useful, we will have to do a bit more work.
|
||||
To more efficently train our network these equations are implemented using matrix operations.
|
||||
The error in the output layer is calculated simply as, with \( \hat{t} \) being our targets,
|
||||
|
||||
$$ \delta_L = \hat{t} - \hat{y} = (n_{inputs}, n_{categories}) .$$
|
||||
|
||||
<p>
|
||||
The choice of <em>hyperparameters</em> such as learning rate and regularization parameter is hugely influential for the performance of the network. Typically a <em>grid-search</em> is performed, wherein we test different hyperparameters separated by orders of magnitude. For example we could test the learning rates \( \eta = 10^{-6}, 10^{-5},...,10^{-1} \) with different regularization parameters \( \lambda = 10^{-6},...,10^{-0} \).
|
||||
The gradient for the output weights is calculated as
|
||||
|
||||
$$ \nabla W_{L} = \hat{a}^T \delta_L = (n_{hidden}, n_{categories}) ,$$
|
||||
|
||||
<p>
|
||||
Next, we haven't implemented minibatching yet, which introduces stochasticity and is though to act as an important regularizer on the weights. We call a feed-forward + backward pass with a minibatch an <em>iteration</em>, and a full training period
|
||||
going through the entire dataset (\( n/M \) batches) an <em>epoch</em>.
|
||||
where \( \hat{a} = (n_{inputs}, n_{hidden}) \). This simply means that we are summing up the gradients for each input.
|
||||
Since we are going backwards we have to transpose the activation matrix.
|
||||
|
||||
<p>
|
||||
If this does not improve network performance, you may want to consider altering the network architecture, adding more neurons or hidden layers.
|
||||
Andrew Ng goes through some of these considerations in this <a href="https://youtu.be/F1ka6a13S9I" target="_self">video</a>. You can find a summary of the video <a href="https://kevinzakka.github.io/2016/09/26/applying-deep-learning/" target="_self">here</a>.
|
||||
The gradient with respect to the output bias is then
|
||||
|
||||
$$ \nabla \hat{b}_{L} = \sum_{i=1}^{n_{inputs}} \delta_L = (n_{categories}) .$$
|
||||
|
||||
<p>
|
||||
The error in the hidden layer is
|
||||
|
||||
$$ \Delta_h = \delta_L W_{L}^T \circ f'(z_{h}) = \delta_L W_{L}^T \circ a_{h} \circ (1 - a_{h}) = (n_{inputs}, n_{hidden}) ,$$
|
||||
|
||||
<p>
|
||||
where \( f'(a_{h}) \) is the derivative of the activation in the hidden layer. The matrix products mean
|
||||
that we are summing up the products for each neuron in the output layer. The symbol \( \circ \) denotes
|
||||
the <em>Hadamard product</em>, meaning element-wise multiplication.
|
||||
|
||||
<p>
|
||||
This again gives us the gradients in the hidden layer:
|
||||
|
||||
$$ \nabla W_{h} = X^T \delta_h = (n_{features}, n_{hidden}) ,$$
|
||||
|
||||
$$ \nabla b_{h} = \sum_{i=1}^{n_{inputs}} \delta_h = (n_{hidden}) .$$
|
||||
|
||||
<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"># to categorical turns our integer vector into a onehot representation</span>
|
||||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.metrics</span> <span style="color: #008000; font-weight: bold">import</span> accuracy_score
|
||||
|
||||
<span style="color: #408080; font-style: italic"># one-hot in numpy</span>
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">to_categorical_numpy</span>(integer_vector):
|
||||
n_inputs <span style="color: #666666">=</span> <span style="color: #008000">len</span>(integer_vector)
|
||||
n_categories <span style="color: #666666">=</span> np<span style="color: #666666">.</span>max(integer_vector) <span style="color: #666666">+</span> <span style="color: #666666">1</span>
|
||||
onehot_vector <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((n_inputs, n_categories))
|
||||
onehot_vector[<span style="color: #008000">range</span>(n_inputs), integer_vector] <span style="color: #666666">=</span> <span style="color: #666666">1</span>
|
||||
|
||||
<span style="color: #008000; font-weight: bold">return</span> onehot_vector
|
||||
|
||||
<span style="color: #408080; font-style: italic">#Y_train_onehot, Y_test_onehot = to_categorical(Y_train), to_categorical(Y_test)</span>
|
||||
Y_train_onehot, Y_test_onehot <span style="color: #666666">=</span> to_categorical_numpy(Y_train), to_categorical_numpy(Y_test)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">feed_forward_train</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: #408080; font-style: italic"># for backpropagation need activations in hidden and output layers</span>
|
||||
<span style="color: #008000; font-weight: bold">return</span> a_h, probabilities
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">backpropagation</span>(X, Y):
|
||||
a_h, probabilities <span style="color: #666666">=</span> feed_forward_train(X)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># error in the output layer</span>
|
||||
error_output <span style="color: #666666">=</span> probabilities <span style="color: #666666">-</span> Y
|
||||
<span style="color: #408080; font-style: italic"># error in the hidden layer</span>
|
||||
error_hidden <span style="color: #666666">=</span> np<span style="color: #666666">.</span>matmul(error_output, output_weights<span style="color: #666666">.</span>T) <span style="color: #666666">*</span> a_h <span style="color: #666666">*</span> (<span style="color: #666666">1</span> <span style="color: #666666">-</span> a_h)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># gradients for the output layer</span>
|
||||
output_weights_gradient <span style="color: #666666">=</span> np<span style="color: #666666">.</span>matmul(a_h<span style="color: #666666">.</span>T, error_output)
|
||||
output_bias_gradient <span style="color: #666666">=</span> np<span style="color: #666666">.</span>sum(error_output, axis<span style="color: #666666">=0</span>)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># gradient for the hidden layer</span>
|
||||
hidden_weights_gradient <span style="color: #666666">=</span> np<span style="color: #666666">.</span>matmul(X<span style="color: #666666">.</span>T, error_hidden)
|
||||
hidden_bias_gradient <span style="color: #666666">=</span> np<span style="color: #666666">.</span>sum(error_hidden, axis<span style="color: #666666">=0</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">return</span> output_weights_gradient, output_bias_gradient, hidden_weights_gradient, hidden_bias_gradient
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Old accuracy on training data: "</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(accuracy_score(predict(X_train), Y_train)))
|
||||
|
||||
eta <span style="color: #666666">=</span> <span style="color: #666666">0.01</span>
|
||||
lmbd <span style="color: #666666">=</span> <span style="color: #666666">0.01</span>
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #666666">1000</span>):
|
||||
<span style="color: #408080; font-style: italic"># calculate gradients</span>
|
||||
dWo, dBo, dWh, dBh <span style="color: #666666">=</span> backpropagation(X_train, Y_train_onehot)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># regularization term gradients</span>
|
||||
dWo <span style="color: #666666">+=</span> lmbd <span style="color: #666666">*</span> output_weights
|
||||
dWh <span style="color: #666666">+=</span> lmbd <span style="color: #666666">*</span> hidden_weights
|
||||
|
||||
<span style="color: #408080; font-style: italic"># update weights and biases</span>
|
||||
output_weights <span style="color: #666666">-=</span> eta <span style="color: #666666">*</span> dWo
|
||||
output_bias <span style="color: #666666">-=</span> eta <span style="color: #666666">*</span> dBo
|
||||
hidden_weights <span style="color: #666666">-=</span> eta <span style="color: #666666">*</span> dWh
|
||||
hidden_bias <span style="color: #666666">-=</span> eta <span style="color: #666666">*</span> dBh
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"New accuracy on training data: "</span> <span style="color: #666666">+</span> <span style="color: #008000">str</span>(accuracy_score(predict(X_train), Y_train)))
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
<!-- navigation buttons at the bottom of the page -->
|
||||
@@ -300,7 +396,7 @@ Andrew Ng goes through some of these considerations in this <a href="https://you
|
||||
<li><a href="._NeuralNet-bs054.html">55</a></li>
|
||||
<li><a href="._NeuralNet-bs055.html">56</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-bs047.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
Reference in New Issue
Block a user