Deep Learning_Học sâu
- Tín chỉ
- 6
- Bậc
- Bachelor
- Thang điểm
- 10
- Điểm qua
- 5
Mô tả
In this course, student will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.
Phân bổ thời gian
Study hour (300h) = 90h contact hours + 1h final exam + 209h self-study
Nhiệm vụ sinh viên
- Students must attend at least 80% of contact slots in order to be accepted to the final examination. - Student is responsible to do all exercises, assignments and labs given by instructor in class or at home and submit on time - Use laptop in class only for learning purpose - Promptly access to the FU LMS at http://flm.fpt.edu.vn for up-to-date course information
Công cụ
- Jupyter notebook - Cloud server: 72 hours/project
Lưu ý
1) On-going Assessment - Report 1: Project Proposal [ Oral group presentatation] : 10% - Report 2: Data Tasks [ Oral group presentatation]: 10% - Report 3: Model & Results [ Oral group presentatation]: 30% - Report 4: Final report & Group presentatation: 10% - 1 progress tests: 10% - 1 Final Exam: 30% 2) Final Result 100% Completion Criteria: 1) Every on-going assessment component > 0 2) Final Exam Score >= 4 & Final Result >= 5