1 Here's a sample syllabus for an 1 Here’s a detailed syllabus for an
undergraduate course on Artificial Artificial Intelligence (AI) course Intelligence (AI) tailored for IT focusing on the specified topics: students. This course is designed to Introduction to AI, Supervised provide foundational knowledge, Learning, Unsupervised Learning, Deep practical skills, and an understanding Learning, and Natural Language of the ethical implications of AI. Processing (NLP). This syllabus is designed for IT undergraduates and includes objectives, weekly topics, assignments, and assessments.
11 Course Description 12 This course provides an introduction to the fundamental concepts and techniques of artificial intelligence. Students will explore various AI domains, including machine learning, natural language processing, and computer vision. The course emphasizes practical applications, hands-on projects, and the ethical implications of AI technologies. 13
14 Course Objectives 11 Course Objectives
15 By the end of this course, students 12 By the end of this course, students will be able to: will be able to:
16 Understand the key concepts and 13 Understand the fundamental concepts and terminology of AI. terminology of artificial intelligence. 17 Implement basic AI algorithms and 14 Implement and evaluate supervised and models. unsupervised learning algorithms. 18 Analyze and evaluate AI solutions in 15 Apply deep learning techniques to solve various applications. complex problems. 19 Discuss ethical considerations and 16 Utilize natural language processing societal impacts of AI technologies. methods for text analysis and processing.
20 17
21 Weekly Topics 18 Course Outline
22 Week 1: Introduction to AI 19 Week 1: Introduction to AI
23 History and evolution of AI 20 Topics:
24 Overview of AI applications 21 Definition and scope of AI 25 Week 2: Problem Solving and Search 22 Historical context and evolution of AI Algorithms 26 Problem formulation 23 Overview of AI applications in various fields (healthcare, finance, robotics) 27 Uninformed and informed search 24 Assignment: Write a short essay on a strategies (BFS, DFS, A*) recent AI application and its societal impact. 28 Week 3: Knowledge Representation 25 29 Logic and inference 26 Week 2: Supervised Learning 30 Semantic networks, frames, and 27 Topics: ontologies 31 Week 4: Introduction to Machine 28 Overview of supervised learning Learning 32 Types of learning (supervised, 29 Types of supervised learning algorithms unsupervised, reinforcement) (classification vs. regression) 33 Overview of algorithms (linear 30 Evaluation metrics (accuracy, regression, decision trees) precision, recall, F1-score) 34 Week 5: Supervised Learning Techniques 31 Assignment: Implement a simple supervised learning model (e.g., linear regression or decision tree) using a dataset of your choice. 35 Training models 32 36 Evaluation metrics (accuracy, 33 Week 3: Advanced Supervised Learning precision, recall) Techniques 37 Week 6: Unsupervised Learning 34 Topics: Techniques 38 Clustering algorithms (k-means, 35 Ensemble methods (bagging, boosting) hierarchical) 39 Dimensionality reduction (PCA) 36 Support Vector Machines (SVM) 40 Week 7: Natural Language Processing 37 Model selection and hyperparameter tuning 41 Text processing techniques 38 Assignment: Compare the performance of different supervised learning models on a dataset and report findings. 42 Sentiment analysis and language models 39 43 Week 8: Computer Vision 40 Week 4: Unsupervised Learning 44 Image processing fundamentals 41 Topics: 45 Object detection and recognition 42 Overview of unsupervised learning 46 Week 9: Neural Networks and Deep 43 Clustering techniques (k-means, Learning hierarchical clustering) 47 Basics of neural networks 44 Dimensionality reduction techniques (PCA, t-SNE) 48 Introduction to deep learning 45 Assignment: Apply k-means clustering to architectures (CNNs, RNNs) a dataset and visualize the results. 49 Week 10: Reinforcement Learning 46 50 Markov decision processes 47 Week 5: Advanced Unsupervised Learning Techniques 51 Q-learning and policy gradients 48 Topics: 52 Week 11: AI Ethics and Society 49 Anomaly detection methods 53 Bias in AI 50 Association rule learning (Apriori algorithm) 54 The impact of AI on jobs and privacy 51 Introduction to generative models concerns (GANs) 52 Assignment: Implement an anomaly detection algorithm on a dataset and evaluate its effectiveness. 53 54 Week 6: Deep Learning 55 Topics: 56 Basics of neural networks (architecture, activation functions) 57 Training neural networks (backpropagation, gradient descent) 58 Overview of deep learning frameworks (TensorFlow, Keras) 59 Assignment: Build and train a simple neural network for image classification using TensorFlow/Keras. 60 61 Week 7: Convolutional Neural Networks (CNNs) 62 Topics: 63 Architecture of CNNs 64 Applications of CNNs in image processing 65 Transfer learning and fine-tuning pre- trained models 66 Assignment: Use a pre-trained CNN model (e.g., VGG16, ResNet) to classify images from a new dataset. 67 68 Week 8: Recurrent Neural Networks (RNNs) and Natural Language Processing 69 Topics: 70 Basics of RNNs and LSTMs 71 Applications of RNNs in sequence prediction 72 Introduction to NLP and its importance 73 Assignment: Implement a simple RNN model for text classification. 74 75 Week 9: Natural Language Processing (NLP) Fundamentals 76 Topics: 77 Text preprocessing techniques (tokenization, stemming, lemmatization) 78 Feature extraction methods (Bag of Words, TF-IDF) 79 Introduction to word embeddings (Word2Vec, GloVe) 80 Assignment: Build a text classification model using NLP techniques on a dataset of your choice. 81 82 Week 10: Advanced NLP Techniques 83 Topics: 84 Sequence-to-sequence models and attention mechanisms 85 Introduction to Transformers and BERT 86 Applications of NLP (chatbots, sentiment analysis) 87 Assignment: Create a simple chatbot using NLP techniques and present its functionality. 88 89 Week 11: AI Ethics and Societal Impact 90 Topics: 91 Ethical considerations in AI 92 Bias in AI algorithms 93 The societal impact of AI technologies 94 Assignment: Write a reflective essay on the ethical implications of a chosen AI application. 95
55 Week 12: Final Project Presentations 96 Week 12: Final Project Presentations
56 Student presentations on AI projects 97 Topics:
98 Students present their AI projects 99 Peer feedback and discussion 100 Assignment: Prepare and present a final project that applies concepts learned throughout the course, demonstrating the use of AI techniques.
63 107 64 Required Texts 108 Required Texts 65 Russell, S. J., & Norvig, P. (2021). 109 Russell, S. J., & Norvig, P. (2021). Artificial Intelligence: A Modern Artificial Intelligence: A Modern Approach. 4th Edition. Pearson. Approach. 4th Edition. Pearson.
66 Goodfellow, I., Bengio, Y., & 110 Chollet, F. (2018). Deep Learning with Courville, A. (2016). Deep Learning. Python. Manning Publications. MIT Press. 111 112 Software and Tools 113 Programming Language: Python 114 Libraries: NumPy, pandas, scikit-learn, TensorFlow, Keras, NLTK, spaCy 115 Development Environment: Jupyter Notebook or any preferred IDE (PyCharm, VS Code) 116 117 Course Policies 118 Attendance: Regular attendance is expected and will impact your participation grade. 119 Late Work: Assignments submitted late will incur a penalty unless prior arrangements have been made. 120 Academic Integrity: Students are expected to uphold academic integrity. Any form of cheating or plagiarism will result in disciplinary action. 121 122 Contact Information 123 For any questions or concerns regarding the course, please reach out via email or during office hours. 124 125 This syllabus provides a comprehensive framework for teaching an AI course with a focus on the specified topics. Feel free to adjust any sections to fit your specific needs or institutional guidelines!
