ADA 447

Course Code & Number

ADA 447

Course Title

Introduction to Deep Learning

Level

BS

Credit Hours/ ECTS Credits

(3+0+0) 3 TEDU Credits, 5 ECTS Credits

Year of Study:

Senior

Semester:

Spring

Type of Course:

Elective Free Elective

Mode of Delivery:

Face-to-face

Language of Instruction:

English

Pre-requisite / Co-requisite:

Catalog Description

Fastai framework, state-of-the-art models, theoretical explanations of core deep learning concepts, data preprocessing and augmentation, transfer learning, convolutional neural networks (CNNs), natural language processing (NLP) models, tabular and collaborative filtering models, fine-tuning and optimization, interpretability and deployment, hands-on coding exercises.

Course Objectives

This course aims to equip students with both practical and theoretical skills in deep learning using the fastai framework. Through hands-on projects and in-depth discussions, students will gain experience implementing and fine-tuning state-of-the-art deep learning models for diverse applications, including computer vision, natural language processing, and tabular data. It will enhance their understanding of foundational deep learning concepts while developing their ability to critically evaluate and optimize models. By integrating theory with practice, this course prepares students for advanced roles in AI and machine learning across various industries.

Course Learning Outcomes

Upon the successful completion of the course, students will be able to:

1. Define foundational deep learning concepts, including neural network architectures, optimization techniques, and transfer Learning,
2. Explain the principles of neural network architectures, optimization techniques, and transfer learning in the context of deep Learning,
3. Apply deep learning techniques to implement models for computer vision and natural language processing tasks,
4. Analyze the performance of deep learning models by interpreting results and identifying areas for improvement,
5. Evaluate the effectiveness of different optimization strategies and hyperparameters in fine-tuning state-of-the-art models,
6. Design a deep learning project that integrates theoretical knowledge with practical applications.

Course Coordinator:

Dr. Şafak Özden