The course "Deep Learning for Everyone" provides a comprehensive introduction to the field of deep learning, designed specifically for students with no prior computer background. Over the span of 12 weeks, students will be guided through the fundamental concepts, techniques, and applications of deep learning. Starting with an overview of the field, students will explore the foundations of machine learning and neural networks. They will then delve into various deep learning architectures, such as convolutional and recurrent neural networks, as well as generative adversarial networks. During this course work, practical hands-on experience will be gained through the use of popular deep learning libraries and tools. Additionally, students will learn about data preparation, model training and evaluation, and transfer learning. By end of the course, students will have developed a solid understanding of deep learning principles, acquired practical skills for building and training deep learning models, and be well-prepared to apply deep learning techniques in their respective domains.

There is no need of strong prerequisites for this course. However, basic knowledge of Mathematics, Statistics and Programming Languages is required

Midterm: 20%
Final: 30%
Project: 20%
Homework & Assignments: 30% (Every Week)
Important Notes:
Please note that the evaluation criteria for the course may be subject to changes based on the instructor's discretion and the evolving nature of the curriculum. Any modifications to the evaluation criteria will be communicated to the students well in advance, providing clarity on the updated expectations and assessment methods.
In the course, there will be a mid-term exam and a final exam. The mid-term exam will cover the material taught up to that point, focusing on the topics covered in the initial weeks. The final exam, on the other hand, will encompass the entire course, including all the topics and concepts discussed throughout the duration of the course.
A make-up class will be scheduled to accommodate any classes that fall on public holidays, ensuring that students have the opportunity to cover the missed material and maintain continuity in their learning.

There will be no mandatory requirement for the special books. However, I would like to provide a book recommendation as an additional resource, here are a few popular options:
Deep Learning" by Ian Goodfellow, Machine Learning with PyTorch and Scikit-Learn Book, Deep Learning with Python

1. Introduction to Deep Learning
2: Foundations of Machine Learning
3: Neural Networks Basics
4: Deep Learning Architectures
5: Deep Learning Libraries, Tools and Programming
6: Data Preparation and Preprocessing
Mid Term
7: Model Training and Evaluation
8: Transfer Learning and Fine-tuning
9: Advanced Topics in Deep Learning
10: Handling Large Datasets and Distributed Computing
12: Project Presentations and Conclusion
Final Exam & Project

No quiz but random Q&A will be conducted.
Hands-on experienece.

Original Work: All code and assignments must be the student's own original work.
Collaboration Policy: Clearly define the collaboration policy for assignments.
Plagiarism and Citation: Properly cite external sources and give credit when incorporating them into assignments.
Individual Submission: Each student must submit their own work individually.
Academic Honesty Policy: Communicate the consequences of academic dishonesty, including cheating and plagiarism.
Code Submission Format: Specify the required format for code submission.
Testing and Debugging: Encourage thorough testing and debugging before submitting code.
Proctoring or Monitoring: Explain any proctoring or monitoring measures in place during exams or assessments.
Support and Resources: Provide resources and support for learning and understanding the material.
Discourage Sharing: Discourage students from sharing or exchanging completed assignments.
Penalties for Violations: Clearly state the penalties for academic integrity violations.
Seek Help: Encourage students to seek assistance from instructors or teaching assistants instead of resorting to cheating.