Download presentation
Presentation is loading. Please wait.
1
Introduction to Neural Networks
Neural Network Architecture and Learning
2
Neural Networks Notations
3
Lecture Overview The Neuron Model Neural Networks Architectures
Learning and Learning Rules in Neural Networks.
4
Introduction Artificial neuron models and neural network architectures are generally quite simple. Why are artificial neural networks so powerful in solving computationally complex tasks, such as image/speech understanding, optimisation, and process control? This is because their ability to learn and to generalise.
5
Neuron Model
6
Activation Function
7
Neural Networks Architectures
8
Neural Networks Architecture
9
How to Design a Neural Network for a Given Task
A neural network model consists of : (1)a neuron model (2)interconnection architecture (3)A learning (optimisation) algorithm. The design process includes: (1)Choosing a neuron model (2)Selecting a neural network architecture (3)Collecting training data and developing a learning algorithm (4)Training the network and testing its performance The neural network performance is evaluated by: –Convergence/stability –Accuracy –Storage capacity –Generalisation.
10
Learning in Neural Networks
Learning is a process by which the free parameters (including hyper-parameters controlling the network structure) of a neural network are adapted through a process of stimulation by the environment where the network is embedded. The type of learning is determined by the manner in which the parameter changes take place.
11
Learning Tasks and Performance Measures
12
Hebbian Learning Rule-The oldest rule
13
Learning in Neural Networks
14
Hebbian Learning Rule
15
Competitive Learning Rule
16
Error Correction Learning Rule
17
Performance Improvement through Error Correction Learning
18
Error Gradient Descent Learning Rule
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.