Artificial Intelligence.pptx learn and practice
- 2. Agenda • Introduction of AI • What is AI? • Why AI is important and its case studies • Types of AI • How the Machine Learning is related to AI? • Introduction to Machine Learning • What are the types of machine learning? • Case Studies of machine learning • How Deep Learning is related to ML and AI
- 3. Introduction to AI • Prof. John McCarthy coined the term AI in 1956 at a symposium at Dartmouth College. McCarthy describes artificial intelligence as the "science and engineering of creating intelligent machines, particularly intelligent computer programs." • You may not be aware that you engage with AI systems on a daily basis. When you use a search engine like Google or Bing, communicate with a virtual assistant like Siri, or use an automatic language translation service, you are engaging with intelligent systems.
- 4. The three phases of Computing
- 5. The three phases of Computing • First Phase: The Mechanical Computing Era (1623 - 1945) • This epoch includes the first attempts to automate calculations and computations. • Although it was never completed during his lifetime, Charles Babbage is widely recognized with inventing the first mechanical computer in the early nineteenth century. His Analytical Engine established the basis for modern computing principles. • During this period, devices such as the abacus, slide rule, and mechanical calculators were developed to aid in arithmetic and mathematical operations.
- 6. Second Phase: The Electronic Computing Era (1945 - mid-2000s) • This phase saw the emergence and rapid advancement of electronic computers. • The development of programming languages, operating systems, and the internet were significant milestones during this period, enabling widespread use and accessibility of computers. Third Phase: The AI Computing Era (mid-2000s - present) This stage is distinguished by the incorporation of computing devices into almost every area of daily life. It is concerned with the spread of computing capabilities in numerous forms, such as smartphones, wearable devices, IoT (Internet of Things), cloud computing, and networked systems. This phase is defined by advancements in AI (Artificial Intelligence), machine learning, big data, and the expanding influence of automation.
- 7. Why AI is important?
- 8. Why AI is important? • Artificial Intelligence (AI) holds immense importance and impact across various fields and industries due to several reasons: 1. Automation and Efficiency: 2. Decision Making and Prediction 3. Personalization and Customization 4. Improving Healthcare 5. Enhancing User Experience 6. Automation of Dangerous Tasks 7. Economic Impact 8. Ethical Considerations
- 9. Types of AI • There are two types of AI: 1. Strong AI 2. Weak AI 1. Strong AI: • The first approach builds systems that can act and think intelligently like people do. This approach simulates human reasoning and cognition in general tasks and is called strong AI. Most of these projects are in the small-to-medium size range. The three largest projects are DeepMind, the Human Brain Project (an academic project that is based in Lausanne, Switzerland), and OpenAI.
- 10. 1. Weak AI: • The second approach is not concerned about whether the AI systems display human-like cognitive functions; the focus is on AI systems that perform specific tasks accurately and correctly. This approach is called weak AI. An example of weak AI is a chatbot, which is trained to answer a specific set of questions about a domain. A chatbot does not have self- awareness or genuine intelligence. Evolution of Artificial Intelligence Types: 1. Artificial Narrow Intelligence (ANI) 2. Artificial General Intelligence (AGI) 3. Artificial Super Intelligence (ASI)
- 11. Case studies of AI • Healthcare - IBM Watson for Oncology • Finance - Fraud Detection with Machine Learning • Retail - Amazon's Recommendation System • Transportation - Autonomous Vehicles • Manufacturing - Predictive Maintenance
- 12. Stages of AI: Intelligence or the cognitive process is composed of three main stages: • Observe and input the information or data. • Interpret and evaluate the input that is received from the surrounding environment. • Make decisions as a reaction towards what you received as an input and interpreted and evaluated. • In Inerpet and evaluate stage the AI need to think like Human and make predictions like Human by using the previous data. Here Machine Learning can fulfill this stage and make accurate predictions. • This is how AI and Machine Learning are Related.
- 13. Intoduction to ML: • Machine learning (ML) is a subfield of artificial intelligence (AI) that focuses on the development of algorithms and models that enable computers to learn and make predictions or decisions based on data, without being explicitly programmed for every task. • The primary goal of machine learning is to create systems that can learn from data and improve over time, providing insights, predictions, and solutions to complex problems.
- 15. Basic Concepts in Machine Learning: Data: • Data forms the foundation of machine learning. It consists of observations, measurements, or information used by ML algorithms to learn patterns, make predictions, or perform tasks. Data can be structured (in databases or spreadsheets) or unstructured (text, images, audio). Features and Labels: • In supervised learning, data is divided into features (input variables) and labels (output or target variables). The model learns to map features to labels by identifying patterns and relationships in the data.
- 16. Python Libraries in ML: • Tensor Flow • Pytorch • Numpy • Pandas • Scikit-learn • SciPy • Keras • Seaborn • Natural Language Tool Kit
- 17. Types of Machine Learning: • Supervised Machine Learning • Unsupervised Machine Learning • Reinforcement Machine Learning
- 18. Supervised Machine Learning: • Supervised Machine Learning is a machine learning approach that’s defined by its use of labeled datasets. These datasets are designed to train or “supervise” algorithms into classifying data or predicting outcomes accurately. Using labeled inputs and outputs, the model can measure its accuracy and learn over time. • Supervised learning can be separated into two types of problems: 1. Classification 2. Regression