Python: Advanced Guide to Artificial Intelligence

Lasso regularization

We define the lasso parameter to have the value 0.8:

lasso_param = tf.Variable(0.8, dtype=tf.float32)lasso_loss = tf.reduce_mean(tf.abs(w)) * lasso_param

Setting the lasso parameter as zero means no regularization as the term becomes zero. Higher the value of the regularization term, higher the penalty. The following is the complete code for lasso regularized regression to train the model in order to predict Boston house pricing:

The code below assumes that train and test datasets have been split as per the previous example.

num_outputs = y_train.shape[1]num_inputs = X_train.shape[1]x_tensor = tf.placeholder(dtype=tf.float32,                          shape=[None, num_inputs], name='x')y_tensor = tf.placeholder(dtype=tf.float32, shape=[None, num_outputs], ...