You are on page 1of 15

EEE430 - AUTONOMOUS SYSTEMS

SESSION 03

Kasun Herath BTech Hons (Eng), MSc (UoM), Dip in CS (UCD)

kasunkh@sltc.ac.lk
31st March 2023
ARTIFICIAL INTELLIGENCE (AI)
What is Artificial Intelligence (AI)?

• Artificial intelligence (AI) is intelligence demonstrated by machines, as opposed


to the natural intelligence displayed by animals and humans.

• AI research has been defined as the field of study of intelligent agents, which
refers to any system that perceives its environment and takes actions that
maximize its chance of achieving its goals.
ARTIFICIAL INTELLIGENCE (AI)
What is Artificial Intelligence (AI)?

• Artificial intelligence (AI) is intelligence


demonstrated by machines, as opposed to the
natural intelligence displayed by animals and
humans.

• AI research has been defined as the field of


study of intelligent agents, which refers to any
system that perceives its environment and
takes actions that maximize its chance of
achieving its goals.
MACHINE LEARNING (ML)
What is Machine Learning (ML)?

• Machine learning (ML) is a field of inquiry devoted to


understanding and building methods that 'learn', that is,
methods that leverage data to improve performance
on some set of tasks.

• It is seen as a part of artificial intelligence. Machine


learning algorithms build a model based on sample
data, known as training data, in order to make
predictions or decisions without being explicitly
programmed to do so.
INTELLIGENT CONTROL TECHNIQUES
• Intelligent control is a class of control techniques that use various AI
computing approaches.
• Intelligent control can be divided into the following major sub-domains:
o Neural network control
o Bayesian control
o Fuzzy (logic) control
o Neuro-fuzzy control
o Expert Systems
o Genetic control
o Intelligent agents
ARTIFICIAL NEURAL NETWORK (ANN)
• ANN is a computational model that consists of
several processing elements that receive inputs
and deliver outputs based on their predefined
activation functions.

• Neural Networks are trying to imitate abilities


of the human and animal brains.

• Artificial neural networks tries to introduce


brain functionalities to a computer by copying
behaviour of nervous systems.
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Human Neuron Vs Artificial Neuron

• ANNs are composed of artificial


neurons which are conceptually derived from
biological neurons.

• Each artificial neuron has inputs and produces


a single output which can be sent to multiple
other neurons.
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Architecture of the Artificial Neural Network
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Architecture of the Artificial Neural Network (Cont’d)

• The neurons are typically organized into multiple layers, especially in deep
learning.

• Neurons of one layer connect only to neurons of the immediately preceding and
immediately following layers.

• The layer that receives external data is the input layer. The layer that produces the
ultimate result is the output layer.
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Architecture of the Artificial Neural Network (Cont’d)

Neural Network (NN) consist of

• One input layer


• One or more hidden layers
• One output layer
• A set of weights and biases between each layer
• Activation function for each hidden layer
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Architecture of the Artificial Neural Network (Cont’d)

In general, there are three types of network architectures.

1. Single-Layer Feedforward Networks

2. Multi-Layer Feedforward Networks

3. Recurrent Networks
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Neural Network Topologies
Neural Network (NN) topologies are describe how neurons map to each other.
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Activation Function
• An Activation Function decides
whether a neuron should be
activated or not.
• This means that it will decide
whether the neuron’s input to the
network is important or not in the
process of prediction using
simpler mathematical operations.
ARTIFICIAL NEURAL NETWORK (ANN) (CONT’D)
Activation Function (Cont’d)
THANK YOU

The Future of AI

“The future depends on some graduate student who is deeply suspicious of


everything I have said.”
— Geoffrey Hinton

You might also like