Introduction to Artificial Intelligence (AI) and Machine Learning

Introduction to Artificial Intelligence (AI) and Machine LearningArtificial Intelligence

Artificial Intelligence (AI) is a way to make machines think and behave intelligently. These machines are controlled by software inside them, so AI has a lot to do with intelligent software programs that control these machines. AI is also Intelligence demonstrated by machines  replicating the human capability.

It is a science of finding theories and methodologies that can help machines understand the world and accordingly react to situations in the same way that humans do.

Applications of AI

• Computer Vision: These are the systems that deal with visual data such as images and videos. These systems understand the content and extract insights based on the use case.

• Natural Language Processing: This field deals with understanding text. We can interact with a machine by typing natural language sentences. Search engines use this extensively to deliver the right search results.

• Speech Recognition: These systems are capable of hearing and understanding spoken words. Speech recognition is the ability of a machine or program to identify words and phrases in spoken language and convert them to a machine-readable format

• Expert Systems: These systems use AI techniques to provide advice or make decisions. They usually use databases of expert knowledge areas such as finance, medicine, marketing, and so on to give advice about what to do next.

•  Games: AI is used extensively in the gaming industry. It is used to design intelligent agents that can compete with humans

• Robotics: Robotic systems actually combine many concepts in AI. These systems are able to perform many different tasks. Depending on the situation, robots have sensors and actuators that can do different things.

Branches of AI

• Machine learning and pattern recognition: This is perhaps the most popular form of AI out there. We design and develop software that can learn from data. Based on these learning models, we perform predictions on unknown data.

• Logic-based AI: Mathematical logic is used to execute computer programs in logic-based AI. A program written in logic-based AI is basically a set of statements in logical form that express facts and rules about a particular problem domain. This is used extensively in pattern matching, language parsing, semantic analysis, and so on.

• Search: The Search techniques are used extensively in AI programs. These programs examine a large number of possibilities and then pick the most optimal path.

• Knowledge representation: The facts about the world around us need to be represented in some way for a system to make sense of them. The languages of mathematical logic are frequently used here. If knowledge is represented efficiently, systems can be smarter and more intelligent.

•  Planning: This field deals with optimal planning that gives us maximum returns with minimal costs.

• Heuristics: A heuristic is a technique used to solve a given problem that's practical and useful in solving the problem in the short term, but not guaranteed to be optimal. This is more like an educated guess on what approach we should take to solve a problem.

• Genetic programming: Genetic programming is a way to get programs to solve a task, by mating programs and selecting the fittest.

Machine Learning

Machine Learning(ML) is the science of creating algorithms and program which learn on their own. Once designed, they do not need a human to become better. 

Machine Learning is the subfield of computer science that "gives computers the ability to learn without being explicitly programmed". 

“A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E”.

Applications and uses

• Manufacturing

• Demand forecasting
• Telemeters
• Predictive maintenance  

•     Retail
• Predictive Inventory planning
• Recommendation engine 
• Market Segmentation and targeting 
• Customer ROI and lifetime value

• Healthcare and lifescience

• Alerts and diagnostics from real time patient data
• Disease identification
• Proactive healthcare management

• Financial services

• Risk analytics and regulation
• Cross selling and upselling

• Others
• Commuting
• Google’s AI-Powered Predictions (Dijkstra’s algorithm)
• Ridesharing Apps Like Uber and Lyft
• Commercial Flights Use an AI Autopilot

• Email
• Spam Filters
• Smart Email classification (primary, social, and promotion inboxes) 
• Introduction of Smart reply to your inbox ( provides quick smart replies based on email context)
• Grading & Assessment 
• Plagiarism Checkers
• Robo-readers
• AI at Home
• Social Networking ( facebook , Pininterest , Instagram , snapchat )
• Online Shopping
• Search
• Recommendations
• Fraud Protection
• Mobile use
• Voice to text (Google uses artificial neural networks to power voice search.)
• Smart personal Assistants ( Alexa, Google Assistant  , Echo dot , Siri , G-home ) etc 
• Facebooks – JARVIS server ( Integrated home solutions )

Types of Learning

• Supervised Learning: This is a learning process for generalizing on problems where a prediction is required. A “teaching process” compares predictions by the model to known answers and makes corrections in the model.

•  Regression

• Predict continuous valued output (ex. price). 

• Ex. You have a large inventory of items. You want to predict the average price of items  that will sell over the next 3 months.

• Classification

• Discrete valued output (0 or 1; Yes or No)

• Ex: You’d like software to examine individual customer accounts, and for each account decide if it has been hacked / compromised.

• Un-Supervised Learning:

• This is a learning process for generalizing the structure in the data where no prediction is required. 
• Natural structures are identified and exploited for relating instances to each other.

• Ex: Social Network analysis, Market segmentation, Astronomical data analysis etc.

Programming language used for ML

• Python

• Scikit-learn
• TensorFlow
• Theano
• Keras
• PyBrain

• R

• Caret (Classification And REgression Training)
• MLR (Machine Learning in R)

• Java

• WEKA (Waikato Environment for Knowledge Analysis, University of Waikato)
• JDMP (Java Data Mining Package)
• Mlib (SPARK)   
  

• C++

• mlpack
• Shark
• Shogun

• Julia

• ScikitLearn.jl

• Scala

• ScalaNLP

You might also like :

 Internetof Things (IOT) Basics

 Pythontutorial for beginners(Python Basics)

 AndroidSensor - Tutorial

Did you find our blog helpful ? Share in comment section. Feel free to share on Twitter or Facebook by using the share buttons