Machine learning is widely used in many applications including autonomous vehicles, robotics, and medical diagnosis. Recognition of an image is one of the best examples of machine learning or artificial intelligence. Topics of the image recognition course includes fundamental components of deep learning such as convolution layer, full connection layer, pooling layer, ReLU layer, and a softmax layer. In this course, students develop and train their network with matlab by themselves.
Students are expected to
(i) gain an ability to build and learn deep neural networks,
(ii) gain an ability to use numerical computing environments using MATLAB to solve engineering problems,
(iii) gain practical skill to apply the deep learning techniques such as momentum, data arugumentation and filter setting, after taking this course.
✔ Applicable | How instructors' work experience benefits the course |
---|---|
A faculty who has a private company experience gives a lecture. |
Object recognition, Convolutional neural network (CNN), Deep learning, matlab
✔ Specialist skills | ✔ Intercultural skills | Communication skills | Critical thinking skills | ✔ Practical and/or problem-solving skills |
This class is a kind of active learning. Instructor will give some information, but students are required to develop their matlab code.
Course schedule | Required learning | |
---|---|---|
Class 1 | Introduction of course, cifar-10, and sample network, GUI | To run the sample network |
Class 2 | One hot encoding, softmax, MSEloss, KL-divergence, cross-entropy loss | To compare MSE loss and cross-entropy |
Class 3 | Convolution and activation, ReLU, LReLU, PReLU | To compare ReLU, LReLU and PReLU |
Class 4 | Pooling layer and dropout | To compare different parameter of dropout |
Class 5 | Merge layer and batch normalization | To try Batch normalization |
Class 6 | Optimization and data augumentation | To compare sgd and adam |
Class 7 | Parameter tuning 1 | To try parameter tuning |
Class 8 | Parameter tuning 2 | To try parameter tuning |
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
None
None
Assignments and report
None
Students need to implement the matlab code by themselves.
Student who took the course of Computational Imaging (#SCE.I501) cannot take this course.