ABOUT THE COURSE!
Deep learning can be considered as a subset of machine learning. It is a field that is based on learning and improving on its own by examining computer algorithms. While machine learning uses simpler concepts, deep learning works with deep neural networks, which are designed to imitate how humans think and learn.
The fourth course of the Data Science Program aims at providing you a fundamental of modern neural networks and their various applications on computer vision and natural language processing. Furthermore, learners will be able to build Deep Neutral Networks models with two of the most popular deep learning library – Tensorflow and Keras provided by Google. Various optimization techniques also have been taught for fine-tuning a DNN model.
To begin the course, let's take a few minutes to explore the course site. Review the material we’ll cover each week, and preview the assignments/projects/quizzes you’ll need to complete to pass the course.
Main concepts are delivered through videos, demos and hands-on exercises.
|| Introduction to Deep Learning
||6 weeks. Student should allocate at average of 2 hours/ day to complete the course.
After taking this course, the students should all be able to:
- Comprehend about gradient descent, stochastic gradient descent, regularization, overfitting
- Acquire overview and basic knowledge about deep neural network
- Introducing Deep Learning in Computer Vision. Be able to apply CNN and transfer learning to computer vision tasks.
- Acquire overview and basic knowledge about unsupervised representation learning in deep learning as autoencoder, word embedding.
- Introducing Deep Learning in NLP/sequence models. Be able to apply RNN, LSTM to GRU to NLP tasks.
- Proficiently manipulate typical and basic libraries in machine learning with Python: Numpy, Tensorflow, Keras.
Module 1 - Simple Neutral Network
- Lesson 1: Introduction to Optimization
- Lesson 2: Stochastic methods for optimization
- Lesson 3: Introduction to Neutral Network
Module 2 - Deep Learning in Computer Vision
- Lesson 4: Deep Learning Framework
- Lesson 5: Deep Learning for Images
- Lesson 6: Applications of CNNs
Assignment 1 - Project - Image Classification
Module 3 - Unsupervised Representation Learning
- Lesson 7: Unsupervised Learning
Module 4 - Deep Learning in Natural Language Processing
- Lesson 8: Word Embedding
- Lesson 9: Introduction to RNN
- Lesson 10: Modern RNNs
Assignment 2 - Project - Toxic comment classification
M.Sc. Nguyen Hai Nam
- Chief Mentor & Course Designer at FUNiX
- Master of Computer Science, University of Cassino, Italy
- Bachelor of Applied Science, Telecommunications Engineering, PTIT
- Research fields: Deep Learning, Computer vision, Handwritting OCR, Abnormal detection
- Online profile: https://www.linkedin.com/in/hai-nam-nguyen-474587119/
M.S. Vu Thuong Huyen
- Data Scientist at FPT Software Company Limited – a subsidiary of FPT Corporation
- Master of Software engineering, VNU University of Engineering and Technology
- Bachelor of Engineering, School of Applied Mathematics and Informatics, Hanoi University of Science and Technology
- Research fields: Machine learning, Deep learning, Reinforcement Learning, Natural Language Processing…
- Profile online: https://www.linkedin.com/in/thuong-huyen-3969747a/
REVIEWERS & TESTER
Ph.D. Dang Hoang Vu
- FPT Science Director
- Ph.D. in Mathematics, University of Cambridge
- Core member of R&D activities in FPT Corporation
- Main responsibility in analytics side of FPT’s Data Management Platform and data science research
B.A. Ho Quoc Bao
- Research Assistant, Exchange Master Student in Micro and Nano Technology, University of South Eastern Norway
- Master Student in Telecommunication Engineering, HCMUT
- Bachelor of Electronics and Telecommunications Engineering, HCMUT
- Research fields: Signal Processing, Modelling, Machine Learning, Optical cable, Ultrasound Signal
- Online profile: https://www.linkedin.com/in/quoc-bao-ho-bb239288/
Assoc. Prof. Tu Minh Phuong
Ph.D. Nguyen Van Vinh
Ph.D. Tran The Trung
- Dean of IT Faculty, Posts and
Telecommunications Institute of Technology (PTIT)
- Expert & technological consultant in AI & machine learning
- Head of Machine Learning &
Application laboratory in PTIT
- Lecturer & core member of AI Lab, University of Technology - VNU
- AI expert & consultant for DPS, Fsoft
- Ph.D. in Computer Science, Japan Advanced Institute of Science &
- Bachelor’s degree in IT, University of Science, VNU
- Director of FPT Technology
Research Institute, FPT University
- Ph.D. in Computational Physics, UVSQ Université de Versailles Saint-Quentin-en-Yvelines
- M.S. in Astrophysics, Pierre & Marie Curie University
- B.S. in Theoretical & Mathematical Physics, University of Melbourne
Below is the list of all free massive open online learning sources (MOOC) from Coursera used for this course by FUNiX:
In modern times, each subject has numerous relevant studying materials including printed and online books. FUNiX Way does not provide a specific learning resource but offers recommendation for students to choose the most appropriate source to them. In the process of studying from many different sources based on that personal choice, students will be timely connected to a mentor to respond to their questions. All the assessments including multiple choice questions, exercises, projects and oral exams are designed, developed and conducted by FUNiX.
Learners are under no obligation to choose a fixed learning material. They are encouraged to actively find and study from any appropriate sources including printed textbooks, MOOCs or websites. Students are on their own responsibilities in using these learning sources and ensuring full compliance with the source owners’ policies; except for the case in which they have an official cooperation with FUNiX. For further support, feel free to contact FUNiX Academic Department for detailed instructions.
Learning resources are recommended below. It should be noted that listing these learning sources does not necessarily imply that FUNiX has an official partnership with the source’s owner: Coursera, tutorialspoint, edX Training, Udemy, Machine Learning cơ bản, or Towards Data Science.
FUNiX is ready to receive and discuss all comments and feedback related to learning materials via email firstname.lastname@example.org