Overview of Artificial Intelligence
Artificial intelligence (AI) is a research field that studies how to comprehend the intelligent human behaviours on a computer. The final goal of Artificial intelligence is to make a computer that can learn, plan, and solve problems unconventionally. We still cannot make a computer that is as intelligent as a human in all aspects even though the studies have gone beyond half century on AI. However, we have many successful applications. In a few cases, the computer’s that are equipped with AI technology can be even more intelligent than us.
A few research topics in AI are problem solving, reasoning, planning, natural language understanding, computer vision, automatic programming, machine learning, and so on. However, these topics are closely related with each other. For example, the knowledge acquired through learning can be used both for reasoning and also for problem solving. The methods for problem solving are useful for planning and reasoning.
Duration
2 Days
Prerequisite for Artificial Intelligence
- Strong grip on Mathematics
- Strong knowledge of programming languages
- Writing algorithm for finding patterns and learning
- Strong data analytics skills
- Good knowledge of Discrete mathematics
- Strong determination to learn machine learning languages
Course Outline for Artificial Intelligence
Artificial Intelligence Introduction
- Understanding the difference between Machine learning, Deep learning, Data Science, Artificial Intelligence
- Artificial Intelligence in Real World-Applications
- Use Cases in Telecom field
- Artificial Intelligence project life cycle
- Learning paths for various skill sets
Artificial Intelligence Architecture
- Practical aspects of implementation
- Components of AI Architecture
Tools and platforms used in Artificial Intelligence
- Cloud based platforms
- Proprietary tools
- Open source tools, Platforms
Data Preparation for Analysis –General tasks and tools
- Feature pre-processing
- Exploratory Data Analysis
- Data Validation rules
- Data cleaning techniques
- Data Preparation for analysis
- Distance metrics
Artificial Intelligence
- Algorithms used in AI
Model Fine Tuning Selection and Cross validation
- Model accuracy check various techniques Overview – MSE, Confusion Matrix, Accuracy
- How to validate a model?
- What is a best model?
- Types of data
- Types of errors
- Improve accuracy of a model
Case Study –Use cases
- AI Best Practices
- Debugging Strategies