Neural Networks for Pattern Recognition

An Introductory Course in Artificial Intelligence and Data Mining for Scientists, Engineers, Econometrists and other Applied Scientists

 

About This Course: Neural networks (NNs), or artificial neural networks (ANNs), are a computational model used in machine learning, computer science and other research disciplines. From a mathematical viewpoint, the study of neural networks begun around the 1940s. The goal of the neural network is to solve problems – usually modelling and classification problems – by mimicking humans. Neural networks study is all about doing useful computations. Simply, it is endowing computers the ability (that is, techniques) to reason like we humans do – that is, endowing computers with artificial intelligence. Humans are very good in learning from examples; by modelling relationships from data, neural networks allow computers to extract relationship (i.e. learn) from examples. Note, by techniques, we mean computer codes.

 

This course is a comprehensive treatment of the fundamentals of neural networks from the perspective of pattern recognition. It will focus on the mathematical details and the applications of neural networks. It will introduce the basic concepts of pattern recognition, the techniques for modelling probability density functions, the properties of the multi-layer perceptron and the radial basis function network models, and more.

 

Applications of neural networks include autopilot aircrafts in aerospace industry; automobile guidance systems; military weapon orientation and steering; real estate appraisal, loan and mortgage screening, bond rating, portfolio trading computer programs, corporate financial analysis, and currency value prediction; manufacturing process control; cancer cell analysis, prosthetic design, and transplant time optimizer in medical sciences; speech recognition; image and data compression, automated information services, and real-time spoken language translation in telecommunications; face and optical character recognition; natural calamities’ prediction; and many more.

 

Training Cost: ₦ 315,000.00    

Course Dates: 
Saturday 6 January 2018 – Saturday 10 March 2018

 

Course Time: Saturdays, 6pm – 9pm, 6 Jan – 10 Mar 2018

 

Prerequisites: Basic IT skills and basic programming skills in any programming language. Our Scientific Programming Using Python course, Data Science with R course or Scientific Programming with C++ course would be an ideal introduction to this course. Also, a first year undergraduate-level mathematics or background in engineering, physics, mathematics, economics, finance or another applied science with some mathematical content will be helpful.

 

MAKING A BOOKING

Information on how to book one or more of our courses can be found here .

 

Some Applications of Neural Network for Pattern Recognition

   •     Character Recognition

 

nn01.png

 

 

   •     A Self-driving Car

 

nn01a.jpg

 

 

   •     Machine Learning with NN for an Embedded System

 

nn02.png

 

 

   •     The Classification of Complex Geographic Datasets

 

nn03.jpg

 

 

   •     Neural Network for Accelerometer Data Processing

 

nn04.png

 

 

   •     Deep Learning for Computational Biology

 

nn06.jpg

 

 

   •     Robot Cognitive Control

 

nn07.jpg

 

 

   •     Self-driving Car Computer Vision System

 

nn08.jpg

 

Availability Type: 
UPCOMING COURSES
Key Features
Neural networks explained in a multi-disciplinary context
Extensive graphical illustrations of complex mathematical concepts for quick and easy understanding
In-depth neural networks for linear and nonlinear prediction, classification, clustering and forecasting
Covers model development and interpretation of results, data pre-processing, input selection, model development and validation, model uncertainty assessment, and many more.
Lessons
Introduction to Neural Networks
Single-Layer Networks
The Multi-Layer Perceptron
Radial Basis Function Neural Networks
Learning & Generalisation
Pattern Recognition Applications
Neuro-Fuzzy Systems