You are on page 1of 10

NEURAL NETWORKS

UNIT 3
Machine Learning Using Neural Network
 “The term "Artificial Neural Network" is
derived from Biological neural networks that
develop the structure of a human brain.
 Similar to the human brain that has neurons
interconnected to one another, artificial
neural networks also have neurons that are
interconnected to one another in various
layers of the networks.
 These neurons are known as nodes
Feed forward Networks
 A Feed Forward Neural Network is an
artificial neural network in which the
connections between nodes does not
form a cycle.
 The feed-forward model is the basic
type of neural network because the
input is only processed in one
direction.
 The data always flows in one direction
and never backwards/opposite.
Adaptive Networks
 Adaptive artificial neural networks are a
class of networks used in dynamic
environments.
 They are characterized by online
learning.
 A number of techniques are used to
provide adaptability to neural networks:
adaptation by weight modification, by
neuronal property modification, and by
network structure modification.
Supervised Learning Neural Networks
 Supervised learning, also known as supervised machine
learning, is a subcategory of machine learning and artificial
intelligence.
 Supervised learning is a type of machine learning in which a
model is trained on labeled data to make predictions about
new, unseen data.
 Supervised learning is useful for grouping data into categories.
Radial Basis Function Networks
 The popular type of feed-forward
network is the radial basis function (RBF)
network. It has two layers, not counting
the input layer, and contrasts from a
multilayer perceptron in the method that
the hidden units implement
computations.
 The output layer of an RBF structure is
similar to that of a multilayer
perceptron.
Reinforcement Learning
 Reinforcement learning is about an
autonomous agent taking suitable actions
to maximize rewards in a particular
environment.
 Over time, the agent learns from its
experiences and tries to adopt the best
possible behavior.
 we limit human interaction to changing
the environment states, and the system of
rewards and penalties.
Unsupervised Learning Neural Networks
 An unsupervised neural network is a type of artificial neural
network (ANN) used in unsupervised learning tasks.
 Unlike supervised neural networks, trained on labeled data with
explicit input-output pairs, unsupervised neural networks are
trained on unlabeled data.
 In unsupervised learning, the network is not under the guidance of
features.
 These neural networks aim to discover patterns, structures, or
representations within the data without specific guidance.
Adaptive Resonance architectures
 Adaptive resonance theory is a type of
neural network technique developed by
Stephen Grossberg and Gail Carpenter in
1987.
 The term “adaptive” and “resonance”
used in this suggests that they are open
to new learning(i.e. adaptive) without
discarding the previous or the old
information(i.e. resonance).
Advances in Neural networks
1. Game playing and beyond
2. More precision in cancer treatment
3. Progress in Neuro Science
4. AI ad personalized marketing
5. Everyday Interfaces
6. Business Intelligence

You might also like