Supervised Learning Network
Supervised learning is a type of machine learning
where the algorithm learns from labeled training
data to make predictions or decisions.
A supervised learning neural network is a specific
type of artificial neural network that is trained using
labeled input-output pairs.
The network learns to map input data to
corresponding output labels by adjusting its
parameters (weights and biases) during training.
Data Collection and Preparation:
• Gather a dataset containing input samples (features)
along with their corresponding target labels (outputs).
• Split the dataset into two parts: a training set and a
validation set. The training set is used to train the
neural network, while the validation set is used to
evaluate its performance during training.
Network Architecture Design:
• Decide on the architecture of the neural network,
including the number of layers, the number of
neurons in each layer, and the activation functions to
be used.
• Choose an appropriate loss function based on the type
of problem (e.g., mean squared error for regression,
categorical cross-entropy for classification, SVM-
based models Hinge Loss ).
Model Compilation:
• Compile the neural network by specifying the loss
function, optimizer, and evaluation metrics.
• The loss function measures the difference between the
predicted outputs and the actual target labels.
• The optimizer is responsible for updating the network's
weights to minimize the loss.
Optimization Algorithms
Gradient Descent: Updates weights by computing the gradient of the
loss function.
Variants:
Stochastic Gradient Descent (SGD)
Adam Optimizer
RMSprop
Validation:
• Periodically evaluate the network's performance on
the validation set.
• Monitor metrics such as accuracy, precision, recall,
F1 score, etc., to assess how well the network
generalizes to unseen data.
Hyperparameter Tuning:
• Experiment with different hyperparameters (e.g.,
learning rate, batch size, number of layers) to
optimize the network's performance.
• Use techniques like grid search or random search to
find the best combination of hyperparameters.
Testing and Deployment:
• Once satisfied with the network's performance, test it
on a separate test dataset to obtain a final assessment
of its generalization capabilities.
• Deploy the trained model to make predictions on new,
unseen data in real-world applications.
• Supervised learning neural networks are used in a wide
range of applications, including image classification,
object detection, speech recognition, language
translation, medical diagnosis, and more.
• They learn to make accurate predictions by iteratively
adjusting their parameters based on the provided labeled
data.
Backpropagation Network
Auto-associative NNs
The auto-associative neural network is a special kind of MLP -
in fact, it normally consists of two MLP networks connected
"back to back" (see figure below). The other distinguishing
feature of auto-associative networks is that they are trained
with a target data set that is identical to the input data set.
In training, the network weights are adjusted until the
outputs match the inputs, and the values assigned to the
weights reflect the relationships between the various input
data elements.
This property is useful in, for example, data validation:
when invalid data is presented to the trained neural
network, the learned relationships no longer hold and it is
unable to reproduce the correct output.
Ideally, the match between the actual and correct outputs
would reflect the closeness of the invalid data to valid
values. Auto- associative neural networks are also used in
data compression applications.
