Artificial neural networks - artificial intelligence, Computer Engineering

Artificial Neural Networks - Artificial intelligence:

Decision trees, while strong, are a easy representation method. While graphical on the surface, they may be seen as disjunctions of conjunctions, and hence are  logical representation, and we call such type of methods symbolic representations. In this lecture,  we see  at  a non-symbolic  representation  method also known as  Artificial Neural Networks. This term is often reduced to Neural Networks, but this annoys neuron-biologists who deal with actual neural networks (inside our human brains).

As the name shows, ANNs have a biological inspiration, and we concisely look at that first. Following this, we see in detail at how data is represented in ANNs, then we see at the easiest type of network, two layer networks. We see at  perceptions  and  linear  units,  and talk about  the  boundaries  that  such  easy networks have. In the next lecture, we talk about multi-layer networks and the back- propagation algorithm for learning these networks.

Biological Motivation

In our conversation in the very first lecture about how people have reacted the question: "How are we going to have an agent to work intelligently", one of the answers was to realize that  intelligence in  individual humans is resulted by our brains. Neuro - scientists have told us that the brain is made up of architectures of networks of neurons. At the most essential level, neurons may be seen as methods which, when provided some input, will either fire or not fire, depending on the character of the input. The input to fix neurons arises from the senses, but in common, the input to a neuron is a set of outputs from other neurons. If the input to a neuron goes over a fix threshold, then the neuron will fire. In this way, one neuron firing will influence the firing of various other neurons, and information may be stored in terms of the thresholds set and the weight assigned by every neuron to every of its inputs.

Artificial Neural Networks (ANNs) are constructed to mimic the behavior of the brain. Some ANNs are built into hardware, but the wide majority are simulated in software, and we focus on these. It's important not to get the analogy too far, because there actually isn't much similarity between artificial and animal neural networks.  In  particular,  while  the  human  brain  is  predictable  to  contain  around 100,000,000,000 neurons, ANNs usually contain less than 1000 comparable units.

Moreover, the interconnection of neurons is much superior in normal systems. Also, the method in which ANNs store and manipulate information is a gross overview of the way in which networks of neurons work in normal systems.

Posted Date: 10/3/2012 1:18:56 AM | Location : United States

Related Discussions:- Artificial neural networks - artificial intelligence, Assignment Help, Ask Question on Artificial neural networks - artificial intelligence, Get Answer, Expert's Help, Artificial neural networks - artificial intelligence Discussions

Write discussion on Artificial neural networks - artificial intelligence
Your posts are moderated
Related Questions
Problem 1 a) What is the purpose of the CPU and what can the CPU perform. b) Name the two most common types of software and briefly illustrate each one. c) The CPU con

why we don''t use register at the place of ram?

Object Oriented Analysis and Design 1. What are the advantages of object-oriented systems? 2. Describe the Booch Methodology. 3. Justify that UML is a language for modeli

Perform the 23 - 48 operations using the 2's complement method. Ans. Given 23 - 48 firstly add them       23                         0 1 0 1 1 1 - (- 48)                     +

The following are just a few return types of a controller action process. In common an action process can return an instance of an any class that derives from Action Result class.

Parallelism based on Grain size Grain size : Grain size/ Granularity are a measure that defines how much computation is involved in a process. Grain size is concluded by count

Which digital logic family has minimum power dissipation ? Ans. The minimum power dissipation of digital logic family is CMOS. CMOS being an unipolar logic family, occupy a to

Q. Calculations for a standard VGA graphics screen? Let's do the calculations for a standard VGA graphics screen (640×480) using 16 colours. Total number of Pixels = 640 ×48

Q. What is Memory Address Register? Memory Address Register (MAR): It specifies address of memory location from that data or instruction is to be accessed (read operation) or t