26-03-2011, 02:41 PM
[attachment=11075]
Introduction:
A Neural network is analogy to biological neural network in the Human brain.
In other words, A neural network is, in essence, an attempt to simulate the brain
A Neural network is a massively parallel distributed processor made up of simple processing units, which has a propensity for storing experiential knowledge and making it available for use.
Neural networks represent a technology that is rooted in many disciplines: neurosciences, mathematics, statistics, physics, computer science, and engineering.
A neural network is an interconnected group of nodes, akin to the vast network of neurons in the human brain
About biological Neural Networks
• Neurons are primary structural components of Biological neural network.
• Neurons are interconnected by synapses.
• We are born with about 100 billion neurons
• A neuron may connect to as many as 100,000 other neurons
• A Biological neuron
• Neurone vs. Node
• ANNs – The basics
• ANNs incorporate the two fundamental components of biological neural nets:
History of Neural Networks
• McCulloch & Pitts (1943) are generally recognised as the designers of the first neural network
• Many of their ideas still used today (e.g. many simple units combine to give increased computational power and the idea of a threshold)
• Hebb (1949) developed the first learning rule (on the premise that if two neurons were active at the same time the strength between them should be increased)
• During the 50’s and 60’s many researchers worked on the perception amidst great excitement.
• 1969 saw the death of neural network research for about 15 years
• Only in the mid 80’s (Parker and LeCun) was interest revived (in fact Werbos discovered algorithm in 1974)
• Model of a neuron
• Comparison between Feedforward and Recurrent Networks
Feed forward networks:
– Information only flows one way
– One input pattern produces one output
– No sense of time (or memory of previous state)
– Recurrency
– Nodes connect back to other nodes or themselves
– Information flow is multidirectional
– Sense of time and memory of previous state(s)
– Biological nervous systems show high levels of recurrency (but feed-forward structures exists too)
Example: Face Recognition
• From Machine Learning by Tom M. Mitchell
• Input: 30 by 32 pictures of people with the following properties:
– Wearing eyeglasses or not
– Facial expression: happy, sad, angry, neutral
– Direction in which they are looking: left, right, up, straight ahead
• Output: Determine which category it fits into for one of these properties (we will talk about direction)
Introduction:
A Neural network is analogy to biological neural network in the Human brain.
In other words, A neural network is, in essence, an attempt to simulate the brain
A Neural network is a massively parallel distributed processor made up of simple processing units, which has a propensity for storing experiential knowledge and making it available for use.
Neural networks represent a technology that is rooted in many disciplines: neurosciences, mathematics, statistics, physics, computer science, and engineering.
A neural network is an interconnected group of nodes, akin to the vast network of neurons in the human brain
About biological Neural Networks
• Neurons are primary structural components of Biological neural network.
• Neurons are interconnected by synapses.
• We are born with about 100 billion neurons
• A neuron may connect to as many as 100,000 other neurons
• A Biological neuron
• Neurone vs. Node
• ANNs – The basics
• ANNs incorporate the two fundamental components of biological neural nets:
History of Neural Networks
• McCulloch & Pitts (1943) are generally recognised as the designers of the first neural network
• Many of their ideas still used today (e.g. many simple units combine to give increased computational power and the idea of a threshold)
• Hebb (1949) developed the first learning rule (on the premise that if two neurons were active at the same time the strength between them should be increased)
• During the 50’s and 60’s many researchers worked on the perception amidst great excitement.
• 1969 saw the death of neural network research for about 15 years
• Only in the mid 80’s (Parker and LeCun) was interest revived (in fact Werbos discovered algorithm in 1974)
• Model of a neuron
• Comparison between Feedforward and Recurrent Networks
Feed forward networks:
– Information only flows one way
– One input pattern produces one output
– No sense of time (or memory of previous state)
– Recurrency
– Nodes connect back to other nodes or themselves
– Information flow is multidirectional
– Sense of time and memory of previous state(s)
– Biological nervous systems show high levels of recurrency (but feed-forward structures exists too)
Example: Face Recognition
• From Machine Learning by Tom M. Mitchell
• Input: 30 by 32 pictures of people with the following properties:
– Wearing eyeglasses or not
– Facial expression: happy, sad, angry, neutral
– Direction in which they are looking: left, right, up, straight ahead
• Output: Determine which category it fits into for one of these properties (we will talk about direction)
