Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network and its Applications_2012_Oct
- 1. an introduction to Artificial Neural Networks and its applications - Dr. Rajaram Kudli Partners in Co-Creating Success Process, Data and Domain driven Business Decision Life Cycle Introduction to Artificial Neural Networks 1 www.compegence.com
- 2. Artificial Neural Networks Introduction to Artificial Neural Networks 2 www.compegence.com
- 3. Intelligent Systems • What is Intelligence? – The capacity for understanding or the ability to perceive and comprehend meaning - Cognition – System or method able to modify its action in the light of ongoing events - Adaption Introduction to Artificial Neural Networks 3 www.compegence.com
- 4. ABCs of Intelligence • AI - Artificial Intelligence – a branch of Computer Science concerned with the problems of reasoning, knowledge representation, planning, learning, natural language processing, communication, perception etc., thorough the approaches of statistical methods, computational intelligence and symbolic computation, aimed at engineering Intelligent Machines • BI - Business Intelligence – a technology enabled discipline comprising of functions viz., reporting, online analytical processing, data mining, business performance management, benchmarking, predictive & prescriptive analytics etc. that enable an enterprise to discover actionable insights from all its data • CI - Computational Intelligence – a set of nature-inspired computational methodologies and approaches to address complex real-world problems to which traditional approaches, viz., ab-initio modeling or explicit statistical modeling, are ineffective or infeasible Introduction to Artificial Neural Networks 4 www.compegence.com
- 5. Computational Intelligence - Paradigms • Artificial Neural Networks – Human-Like Information Processing • Fuzzy Logic – Human-Understandable Reasoning • Genetic Algorithms – Human-Like Evolution • Chaos Theory – Humanity-Like Complex Behavior Introduction to Artificial Neural Networks 5 www.compegence.com
- 6. Human Understandable Vs Human-Like • Human Understandable • Human-Like – Artificial Intelligence, – Artificial Neural Fuzzy Logic and Genetic Networks; Chaos Algorithms Computing – Synthetic, rule-based – Natural, abstract logical models models – Easier to explain the – Harder to extract knowledge & method of meaning from the solution values – Easier to gain – Harder to gain acceptance acceptance Introduction to Artificial Neural Networks 6 www.compegence.com
- 7. Artificial Neural Networks • Computational models inspired by the human brain – Massively parallel, distributed system, made up of simple processing units., neurons – Synaptic connection strengths among neurons are used to store the acquired knowledge. – Knowledge is acquired by the network from its environment through a learning process Introduction to Artificial Neural Networks 7 www.compegence.com
- 8. Model Complexity NNET HIGH ARIMA AAR MED AR Computational Complexity HWM CM HLES LOW EMA WMA SMA LOW MED HIGH Model Complexity (Forecasting Application) Information Complexity Non-regression Models Regression Models Introduction to Artificial Neural Networks 8 www.compegence.com
- 9. Applicability – Where & Why ? • Where? • Why? – Where data is noisy, – Ability to solve data- complex, imprecise, and intensive problems hi-dimensional – Adaptation – Where a clearly stated – Parallel Distributed mathematical solution or Representation & algorithm doesn’t exist Processing – Where an explanation of – Fault tolerance the decision is not – Nonlinearity required – Scalability – Universality Introduction to Artificial Neural Networks 9 www.compegence.com
- 10. Example – CPG-Retail Sales Forecasting • An Intelligent Forecasting System that evaluates 10 classical forecasting models including Neural Networks, and gives best forecast acceptable to qualitative expectations of a human expert ACTUAL SF_BEST 700 Validation Forecast 600 500 %BEST FC e oa u ni y S l sT t l Qa tt 400 MODEL 300 (1000 SKUs) a 200 NNET 66% 100 AAR 18% 0 9 ARIMA 8% 8 8 8 9 9 9 9 9 9 9 9 9 9 9 0 0 0 0 0 0 0 0 10 0 0 0 1 ct -0 -0 -0 n- 0 b- 0 r-0 r0 - y- 0 -0 l-0 -0 -0 t-0 -0 c- 0 -1 b- 1 -1 r-1 -1 -1 l-1 -1 p- t-1 v- 1 -1 -1 ov ec a e a p a un -J u ug ep c ov e an e ar -A p ay un Ju ug e Oc o ec Ja n -O -N -D -J 4- F 4- M -A -M -J 4 -A 4- S -O 4- N -D -J 4- F M 4- -M 4- J 4- -A -S 4- -N 4- D - 04 4 04 04 04 04 04 0 04 04 4 04 04 04 0 4 04 0 04 04 HW 2% 0 0 0 0 0 0 0 0 0 0 0 Week End Date 8 7 Validation Forecast HOLT 1% 6 CR 0% a s oa u ni y 5 S le T t l Q a tt AR 1% 4 3 EMA 0% 2 WMA 2% 1 SMA 2% 0 -0 8 08 08 09 9 9 9 09 -0 9 9 9 9 9 9 09 10 10 0 0 -1 0 10 0 10 0 -1 0 0 10 11 ct v- c- n- b-0 r0 - r-0 ay - ul -0 g- 0 p- 0 -0 ct v- 0 c- n- b- r1 - r-1 ay n- ul -1 g- p- 1 ct v- 1 c- n- O o e a e M a Ap un J u e O o e a e a Ap u J u e O o De Ja 4- 4- N 4-D 4-J 4-F 4- 4- 4-M 4-J 4- 4-A 4- S 4- 4- N 4-D 4-J 4-F 4-M 4- 4-M 4-J 4- 4-A 4- S 4- 4- N 4- 4- Week End Date Introduction to Artificial Neural Networks 10 www.compegence.com
- 11. Example – Supervised Learning • ALVINN, Autonomous Land Vehicle In a Neural Network, is a perception system which learns to control the NAVLAB vehicles by watching a person drive. Introduction to Artificial Neural Networks 11 www.compegence.com
- 12. Example– Unsupervised Learning • WEBSOM is a method for automatically organizing collections of text documents and for preparing visual maps of them to facilitate the mining and retrieval of information. Introduction to Artificial Neural Networks 12 www.compegence.com
- 13. Example – Associative Memory • Image Storage & Reconstruction by Hopfield network trained on the sample images and then presented with either a noisy cue or a partial cue. Original, Stored Degraded Cue Reconstructed Introduction to Artificial Neural Networks 13 www.compegence.com
- 14. Example - Controls • HOAP, or Humanoid for Open Architecture Platform, represents a fundamentally different approach to creating humanoid robots, in harnessing the power of a neural network to tackle movements and other tasks. Introduction to Artificial Neural Networks 14 www.compegence.com
- 15. Application Areas in Engineering • Aerospace: High performance aircraft autopilots, flight path simulations, aircraft control systems, autopilot enhancements, aircraft component simulations, aircraft component fault detectors • Automotive: Automobile automatic guidance systems, warranty activity analyzers • Electronics: Code sequence prediction, integrated circuit chip layout, process control, chip failure analysis, machine vision, voice synthesis, nonlinear modeling • Mechanical: Condition monitoring, Systems modeling and control • Manufacturing: Manufacturing process control, product design and analysis, process and machine diagnosis, visual quality inspection systems, beer testing, welding quality analysis, paper quality prediction, computer chip quality analysis, analysis of grinding operations, chemical product design analysis, machine maintenance analysis, project bidding, planning and management, dynamic modeling of chemical process systems • Robotics: Trajectory control, forklift robot, manipulator controllers, vision systems • Telecommunications: Data compression, signal processing, pattern recognition: Face, Objects, Fingerprints, Speech recognition; automated information services, real-time translation of spoken language, customer payment processing systems, Equalisers, Network Design, Management, Routing and Control, ATM Network Control, Fault Management, Network Monitoring Introduction to Artificial Neural Networks 15 www.compegence.com
- 16. Application Areas in Business • Business Analytics: Market Research, Market Structure, Market Mix, Customer behavior modeling, Propensity modeling for Purchase, Renewals, Default, Attrition, Fraud, Market & Customer Segmentation • Banking: Credit/Loan application evaluators, Fraud and Risk evaluation, Credit card attrition, Delinquency • Financial: Real estate appraisal, loan advisor, mortgage screening, corporate bond rating, credit line use analysis, portfolio trading program, corporate financial analysis, currency price prediction • Education: Modeling Students’ performance, Personality Profiling, Diagnostics of a modern state, analysis, and forecasting of dynamics of a system of education • Defense: Weapon steering, target tracking, object discrimination, facial recognition, new kinds of sensors, sonar, radar and image signal processing including data compression, feature extraction and noise suppression, signal/image identification; Counter-terrorism • Medical: Breast cancer cell analysis, EEG and ECG analysis, prosthesis design, optimization of transplant times, hospital expense reduction, hospital quality improvement, emergency room test advisement • Securities: Market analysis, automatic bond rating, stock trading advisory systems • Transportation: Truck brake diagnosis systems, vehicle scheduling, routing systems Introduction to Artificial Neural Networks 16 www.compegence.com
- 17. #1 - Predicting Stock Prices • Walkrich Investment Advisors used Neural Networks to produce an investment tool WRRAT based loosely on Warren Buffett's ideas to predict stock prices, and determine which stocks are trading below their market value. The results from January 1995 to January 1996 showed that a Portfolio of WRRAT's most under-priced shares saw an average advance of 33%. Introduction to Artificial Neural Networks 17 www.compegence.com
- 18. #2 - Predicting S&P 500 Index • LBS Capital Management used a neural network software to predict the S&P 500 index. The company uses an expert system to provide instructions to the neural network, which then processes the data accordingly. When tested with hundreds of previous days data the neural network LBS trained predicts the S&P 500 with an accuracy of about 95%. Introduction to Artificial Neural Networks 18 www.compegence.com
- 19. #3 – Predicting Currencies • O'Sullivan Investments successfully used many neural networks in order to advise them of market trends. Mr James O'Sullivan produced an article Neural Nets: A Practical Primer, AI In Finance, 1994 outlined some of the networks used. One of the most important factors in producing a successful net is to ask the right kind of question. Rather than simply ask what the projected price of a currency might be, he asks at what price the market is likely to take off in one direction or the other etc. Introduction to Artificial Neural Networks 19 www.compegence.com
- 20. #4 – Predicting Natural Gas Price • Northern Natural Gas is a regulated wholesaler of natural gas. They must develop and file a rate for the gas they sell based on the average cost of the gas. By developing a neural network that use factors such as the quarter of the year, season, temperature last month etc. to predict the following months oil price, the company was better able to plan rates. Introduction to Artificial Neural Networks 20 www.compegence.com
- 21. #5 – Predicting Bonds • G. R. Pugh & Company does consulting to predict the prices of bonds of public utilities. The company used neural networks to help forecast the following years corporate bond prices and ratings of over 100 public utility companies. The network they used compared very favourably to conventional mathematical analysis. Whereas the network was able to predict a utilities rating (A, B, C) with 95% accuracy, conventional mathematical analysis was only effective 85% of the time. The only difficulties encountered by the network were associated with companies experiencing particularly unusual problems that were not incorporated into the networks inputs. Introduction to Artificial Neural Networks 21 www.compegence.com
- 22. #6 – Direct Mail Marketing • Microsoft used neural networks to maximise the effectiveness of their marketing campaign. Each year the company sent out mail to its registered customers. Most of this mail offered upgrades or new software but the response rate was rather low. The company used a neural network that was fed various variables such as how recently they registered, how many products they have bought etc. to target users more effectively. The results showed an average mailing lead to a 35% cost savings. Introduction to Artificial Neural Networks 22 www.compegence.com
- 23. #7 – Credit Scoring • Research conducted by Dr Herbert Jensen PhD demonstrated that "building a neural network capable of analysing the credit worthiness of loan applicants is quite practical and can be done quite easily". The neural network was trained on no more than 100 loan applications to process application data such as occupation, years with employer etc. Despite the relatively small training set the network achieved a 75-80% success rate. This compared well with more traditional scoring methods that resulted in about a 75% success rate. Introduction to Artificial Neural Networks 23 www.compegence.com
- 24. #8 – Real Estate Appraisal • Several neural networks have been used to predict the sale prices of homes in order to help appraisers assess, sellers estimate asking prices, and home owners decide on improvements. Richard Borst successfully trained a neural network to appraise real estate in the New York area. His network incorporated almost 20 variables including the square feet of living area, age, etc. He used over 200 sales records from 1988 and 1989 to train the network with about 90% accuracy. Introduction to Artificial Neural Networks 24 www.compegence.com
- 25. Summary • ANN can solve the direct (prediction) and inverse (control) problem easy and fast in spite of incompleteness of data • ANN can solve problems of higher complexity of modeling, recognition, predictions, and control in engineering & business, better than traditional solutions • ANN paradigms provide powerful approaches to the problem domains with high contact of theory, simulation, experiment, data and human expertise Introduction to Artificial Neural Networks 25 www.compegence.com
- 26. ANN Paradigms – Theory & Practice • Feed Forward Networks (FFNN) – Multi-Layer Perceptrons (MLP) • Competitive Learning Networks (CLNN) – Self-Organizing Maps (SOM) • Recurrent Neural Networks (RNN) – Hopfield Networks (HNN) Introduction to Artificial Neural Networks 26 www.compegence.com
- 27. Process, Data and Domain driven Information Excellence ABOUT COMPEGENCE Introduction to Artificial Neural Networks 27 www.compegence.com
- 28. Process, Data and Domain Integrated Approach Market Actions Actionable Systemic Decision Excellence Changes Competitive Advantage lies in the exploitation of: Usable Business Process Landscape –More detailed and specific information –More comprehensive Business Timely Infor external data & dependencies Systems Intent mation –Fuller integration –More in depth analysis Business Flexible Usage –More insightful plans and strategies Domain Data –More rapid response to Scalable Cost business events –More precise and apt Sustainable response to customer events Effort Skills & Competency We complement your “COMPETING WITH ANALYTICS JOURNEY” Introduction to Artificial Neural Networks 28 www.compegence.com
- 29. Value Proposition Constraints Decisions? Decisions Tools Alternatives Data Technologies Assumptions Dependencies Trends Concerns / Risks TeraBytes Processes Actions Cost of Ownership Meta data Laye r f or C on sistent Bu sin e ss Unde rstandi ng Actions? Platforms Technology Evolution Sour ceD at Data C usto m D a er ata Extr ct Extrac t a S ginng ta g Ta Tr nsfo r ra m Lo ad A pl ica tion s p at i COMPEGENCE A ssets Busin s Rul s e s e Anal sis y L i a i i t es bl i I n v stm t e en n e ra I t g te Trusted Dashboa ds r T n t ra sla e Da ta C ards Segme n t People R eference D ata (B r nch, P rodu ct ) a P art erD ata n s Repeatable D ri e e v P li g rofi n Fou ndat i n with o Reports Excel DW n I terface C R M/ Marketi g P rograms n Reusable Su m rize m a Pla tf orm Pla tf orm Results Processes Leverage Data Qua lit y and Pro cess Aud it Results? Trade Offs Partners People Reports Cost Ease of Use: Current State Returns Drill Down, Up, Across Time Returns? Dashboards Jump Start the “Process and Information Excellence” journey Focus on your business goals and “Competing with Analytics Journey” Overcome multiple and diverse expertise / skill-set paucity Preserve current investments in people and technology Manage Data complexities and the resultant challenges Manage Scalability to address data explosion with Terabytes of Data Helps you focus on the business and business processes Helps you harvest the benefits of your data investments faster Consultative Work-thru Workshops that help and mature your team Introduction to Artificial Neural Networks 29 www.compegence.com
- 30. Our Expertise and Focus Areas Process + Data + Domain => Decision Analytics; Data Mining; Big Data; DWH & BI Architecture and Methodology Partnered Product Development Consulting, Competency Building, Advisory, Mentoring Executive Briefing Sessions and Deep Dive Workshops Introduction to Artificial Neural Networks 30 www.compegence.com
- 31. Partners in Co-Creating Success Process, Data and Domain driven Information Excellence Process, Data and Domain driven Business Decision Life Cycle www.compegence.com info@compegence.com Introduction to Artificial Neural Networks 31 www.compegence.com