BSTE:IntroductionToPracticalArtificialIntelligence
Revision as of 13:47, 29 August 2022 by R.sirgalina (talk | contribs)
Introduction to Practical Artificial Intelligence
- Course name: Introduction to Practical Artificial Intelligence
- Code discipline: N/A
- Subject area: Artificial intelligence
Short Description
This course covers the following concepts: Practical tools to implement artificial intelligence; Methods and approaches to solving intellectual tasks.
Prerequisites
Prerequisite subjects
Prerequisite topics
Course Topics
| Section | Topics within the section |
|---|---|
| Introduction and reasoning |
|
| Text and speech processing |
|
| Images and video processing |
|
| Machine learning for practice. Recommendations |
|
Intended Learning Outcomes (ILOs)
What is the main purpose of this course?
The course gives a general overview of the history, theoretical basis and technological stack for what we now call "artificial intelligence" (AI). Today AI is not only a research area, but also a complex set of exact algorithms, technologies, frameworks, software and services, which can be easily integrated in modern software. In this course students will learn the history, major theoretical points, structure of knowledge related to AI. The major goal of the course is to practice contemporary AI technologies and frameworks, including reasoning, natural language processing, computer vision, and machine learning. Working individually and in teams, students will solve a variety of AI problems, both from scratch and using existing solutions.
ILOs defined at three levels
Level 1: What concepts should a student know/remember/explain?
By the end of the course, the students should be able to ...
- Ways to present and describe artificial intelligence in software solutions
- The best developed intelligent technologies that perform with near-human quality
- Ideas behind building intelligent systems in reasoning, natural language processing, recommendations, computer vision, speech processing
- Necessary parts to build an intelligent system with computer vision and machine learning technologies
- Factors to decide whether to go for AI or stay in conventional software development approach
Level 2: What basic practical skills should a student be able to perform?
By the end of the course, the students should be able to ...
- Major approaches to construct AI solutions
- Popular libraries and APIs to solve AI tasks
- Algorithms to construct intelligent agents from scratch
- Basic methods of image processing and machine learning
- Major approaches to natural language and speech understanding
Level 3: What complex comprehensive skills should a student be able to apply in real-life scenarios?
By the end of the course, the students should be able to ...
- Create game playing bots using heuristic approaches
- Implement knowledge databases
- Implement systems with speech processing and generation
- Implement image processing and computer vision solutions
- Perform basic data analysis using machine learning
Grading
Course grading range
| Grade | Range | Description of performance |
|---|---|---|
| A. Excellent | 80-100 | - |
| B. Good | 60-79 | - |
| C. Satisfactory | 40-59 | - |
| D. Poor | 0-39 | - |
Course activities and grading breakdown
| Activity Type | Percentage of the overall course grade |
|---|---|
| Labs/seminar classes | 0 |
| Interim performance assessment | 0 |
| Assessments | 60 |
| Exams | 40 |
Recommendations for students on how to succeed in the course
Resources, literature and reference materials
Open access resources
- “Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit,” Steven Bird, Ewan Klein, and Edward Loper. [link]
- Practical Python and OpenCV. [link]
- Ray Kurzweil. The Singularity Is Near: When Humans Transcend Biology. [link]
- Amazon Polly: Text-To-Speech service. [link]
- Get Started with TensorFlow. [link]
- Natural Language Processing with Python. [link]
- Hands-On Machine Learning with Scikit-Learn and TensorFlow. [link]
Closed access resources
Software and tools used within the course
Teaching Methodology: Methods, techniques, & activities
Activities and Teaching Methods
| Learning Activities | Section 1 | Section 2 | Section 3 | Section 4 |
|---|---|---|---|---|
| Development of individual parts of software product code | 1 | 1 | 1 | 1 |
| Homework and group projects | 1 | 1 | 1 | 1 |
| Essays | 1 | 0 | 0 | 0 |
Formative Assessment and Course Activities
Ongoing performance assessment
Section 1
| Activity Type | Content | Is Graded? |
|---|---|---|
| Question | Implement https://en.wikipedia.org/wiki/Nim game bot | 1 |
| Question | Solve simple problems for CLIPS-based expect system completion | 1 |
| Question | Run inference for Bayesian network with given observations | 1 |
| Question | Discuss article in media about artificial intelligence breakthrough | 1 |
| Question | Implement tic-tac-toe bot | 0 |
| Question | Solve non-linear equation with symbolic computation package | 0 |
| Question | Implement Wolfram Alpha bot | 0 |
| Question | Implement decision tree framework | 0 |
Section 2
| Activity Type | Content | Is Graded? |
|---|---|---|
| Question | Build a syntax tree of a sentence | 1 |
| Question | Determine token types for all words in a sentence | 1 |
| Question | Recognize text in a file with speech | 1 |
| Question | Visualize histogram of a wave file | 1 |
| Question | Extract subject and object from a sentence | 0 |
| Question | Visualize text similarity in a dataset with doc2vec and t-SNE | 0 |
| Question | State a problem for symbolic algebra freamework in natural language | 0 |
| Question | Implement a command with a voice message | 0 |
| Question | Implement simple programming language | 0 |
| Question | Detect a chord by a wave file | 0 |
Section 3
| Activity Type | Content | Is Graded? |
|---|---|---|
| Question | Count simple object in a picture | 1 |
| Question | Label objects on a picture | 1 |
| Question | Filter out noisy image | 1 |
| Question | Find contours of cookies on the image | 1 |
| Question | Build an eye detector | 0 |
| Question | Use SIFT descriptors to detect images using bag of words representation | 0 |
| Question | Subtract and measure fishes on a contract background | 0 |
| Question | Track labelled objects in a video | 0 |
Section 4
| Activity Type | Content | Is Graded? |
|---|---|---|
| Question | Run PCA using SVD for a given matrix | 1 |
| Question | Remove unnecessary features | 1 |
| Question | Split a dataset for a k-fold cross-validation | 1 |
| Question | Perform a grid search of hyper-parameters | 1 |
| Question | Find explainable predictors for a real data | 0 |
| Question | Separate cats from dogs in a dataset | 0 |
| Question | Train and estimate a model using k-fold cross-validation | 0 |
| Question | Detect how similar are the interests of 2 users | 0 |
Final assessment
Section 1
- Implement a bot to answer general question on math
- Find local minima and maxima of the function
- Implement an expert system to detect graph cycles
- Implement a bot playing simple board game with minimax algorithm
Section 2
- Implement programming language for a given description
- Implement a bot, that pronounces a fact on a given topic
- Implement comparison of two texts with respect to syntactic complexity
Section 3
- Recognize handwritten text
- Convert chessboard image into notation
- Measure a distance the cat cover in the video
- How many balls are there on the image?
Section 4
- Implement person classifier by voice
- Implement human classifier by face
- Implement recommender system for cold start
- Implement recommender system for a provided dataset
The retake exam
Section 1
Section 2
Section 3
Section 4