Deep Learning Concepts

Deep Learning

• Deep learning is an advanced form of machine learning that simulates the way the human brain learns.
• It creates an artificial neural network that mimics electrochemical activity in biological neurons using mathematical functions.

Artificial Neural Networks

• Artificial neural networks are made up of multiple layers of neurons, defining a deeply nested function.
• This architecture is the reason the technique is referred to as deep learning.
• The models produced by it are often referred to as deep neural networks (DNNs).

Applications of Deep Learning

• Deep neural networks can be used for many kinds of machine learning problems, including:
  • Regression
  • Classification
  • Natural language processing
  • Computer vision

Deep Learning Process

• Deep learning involves fitting training data to a function that can predict a label (y) based on the value of one or more features (x).
• The function (f(x)) is the outer layer of a nested function in which each layer of the neural network encapsulates functions that operate on x and the weight (w) values associated with them.
• The algorithm used to train the model involves:
  • Iteratively feeding the feature values (x) in the training data forward through the layers to calculate output values for ŷ.
  • Validating the model to evaluate how far off the calculated ŷ values are from the known y values (which quantifies the level of error, or loss, in the model).
  • Modifying the weights (w) to reduce the loss.

Training a Deep Learning Model

• The trained model includes the final weight values that result in the most accurate predictions.
• During the training process, the model learns the weights that will result in the most accurate predictions.

Example: Classification using Deep Learning

• In a classification problem, the machine learning model must predict the most probable class to which an observation belongs.
• A classification model predicts a label that consists of the probability for each class.
• In the example of penguin species classification, the feature data (x) consists of four measurements: [x1, x2, x3, x4].
• The label to be predicted (y) is the species of the penguin, with three possible species.
• The predicted label (y) is a vector of three probability values: [P(y=0|x), P(y=1|x), P(y=2|x)].