Home > February, 2009
interested to build new algorithms… what are the basics one needs to know before starting fuzzy logic and neural networks.i am good at c ,c++ and have a little knowledge in visual basic too.what approach should i follow to start from scratch?
I think a background of Theory of Computer Science (Discrete Math, Probability,Graph Theory,State machines,Turing machines) is necessary. Algorithms are programming language independent, so I am not sure how your knowledge of C,C++ is going to help here.Things like algorithm designing are nearer to pure computer science whereas programming is implementation of these algorithms to solve practical problems.As far as reference material is concerned,its here- http://www.google.com! All the best 
powered by Yahoo Answers
I DONT know
powered by Yahoo Answers
I am a maths student in Edinburgh and I am doing my dissertation on the Mathematics behind neural networks. My lecturer wants me to submit a program with the dissertation for an example. It doesn't have to be my own but it needs to illustrate what my dissertation is on. I can't program for toffee! So I wondered if anyone out there would be able to write me a supervised learning neural network program that can read a bitmap of a character (a-z) from a file and recognise what character it is.
Please don't answer if you can't help. There's no point
Interesting.
I can do this for you in C/C++. In fact i do have a neural network that recognizes bitmap formats that i am currently using in a Visually driven robotics system, capturing bitmaps from a live stream in order to direct a robotic arm to pick up an object. However I have used different neural nets for this project RBF,Kohonen and MLP. Let me know your e-mail address and i can send you the appropriate one(s). It would depend on how you have based your dissertation as to which network would be the most appropriate mathematically as you know all differ greatly in relation to the functions that are applied to them. Plus i would need a little extra time to comment the code so you may understand it in a non programming way!!
powered by Yahoo Answers
Where Neural Networks are used now? Where there is a possibility of its usage in future?
For biological neural networks - it is used in 100’s of billions of living organisms.
For artificial neural networks (http://en.wikipedia.org/wiki/Artificial_neural_network) they are the basis for many software programs. See http://en.wikipedia.org/wiki/Neural_network_software for some of lists.
powered by Yahoo Answers
Here's a few that I've looked through that have some good basic information and some other resources for more detailed information:
Back-Propagation Neural Network Tutorial
http://ieee.uow.edu.au/~daniel/software/libneural/BPN_tutorial/BPN_English/BPN_English/
Neural Networks in Plain English
http://www.ai-junkie.com/ann/evolved/nnt1.html
Introduction to Neural Networks
http://www.willamette.edu/~gorr/classes/cs449/intro.htm
Neural Network Theory - A short tutorial
http://documents.wolfram.com/applications/neuralnetworks/index2.html
powered by Yahoo Answers
neural networks were found to be the most appropriate
technique to classify fraud and nonfraud cases .So; the model will combine belief functions and neural networks. I argue that combining these techniques is vital to develop a decision aid to assess fraud
likelihood.
A neural network is an interconnected group of biological neurons. In modern usage the term can also refer to artificial neural networks, which are constituted of artificial neurons. Thus the term 'Neural Network' specifies two distinct concepts:
1. A biological neural network is a plexus of connected or functionally related neurons in the peripheral nervous system or the central nervous system. In the field of neuroscience, it most often refers to a group of neurons from a nervous system that are suited for laboratory analysis.
2. Artificial neural networks were designed to model some properties of biological neural networks, though most of the applications are of technical nature as opposed to cognitive models.
Please see the corresponding articles for details on artificial neural networks or biological neural networks. This article focuses on the relationship between the two concepts.
Neural networks are made of units that are often assumed to be simple in the sense that their state can be described by a single numbers, their "activation" values. Each unit generates an output signal based on its activation. Units are connected to each other very specifically, each connection having an individual "weight" (again described by a single number). Each unit sends its output value to all other units to which they have an outgoing connection. Through these connections, the output of one unit can influence the activations of other units. The unit receiving the connections calculates its activation by taking a weighted sum of the input signals (i.e. it multiplies each input signal with the weight that corresponds to that connection and adds these products). The output is determined by the activation function based on this activation (e.g. the unit generates output or "fires" if the activation is above a threshold value). Networks learn by changing the weights of the connections.
powered by Yahoo Answers
i want to access the ieee papers related to AI and neural networks and fuzzy logic but i dont have an ieee account. could someone suggest me some website or someother source where i can read the ieee papers and other materials related to this area for free .and i also need some help ragrding face recognition and biorecognition using neural networks and fuzzy logic and its practical implementation . i am totally new to this field .i want to start it from the very beginning.please if someone is working in this area kindly help me. thank you.
why not just join…
powered by Yahoo Answers
this is for computer neural networks, not biology type.
There are quite a few, though I don't know if anyone's produced a definitive exhaustive list.
By far, the most common such neural network is the multi-layer perceptron (MLP), also sometimes called a feedforward neural network (FFNN). MLP varies quite a bit in architecture (jump connections, recurrent connections, transfer functions, etc.) and training methods (backpropagation of errors, conjugate gradient, genetic algorithms, etc.).
Some other multilayer artificial neural networks include: cascade correlation neural networks, self-organizing maps (SOM), learning vector quantizers (LVQ), radial basis function (RBF) neural networks (which includes probabilistic neural networks (PNN) and generalized regression neural networks (GRNN)) and restricted Coulomb energy (RCE) neural networks. If one counts the pre-processing acticity as a "layer", there are also functional link networks (FLN) and higher-order neural networks (HONN).
powered by Yahoo Answers
Lectures by Prof. Laxmidhar Behera, Department of Electrical Engineering, Indian Institute of Technology, Kanpur. For more details on NPTEL visit http://nptel.iitm.ac.in
Duration : 0:58:49
Read more »
Technorati Tags: Control, Intelligent, linear, Networks, Neural, Systems
