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 this course include fundamental components of deep learning such as the convolution layer, full connection layer, pooling layer, ReLU layer, and a softmax layer. In this course, students develop and train their network with Pytorch 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 PyTorch to solve engineering problems,
(iii) gain the practical skills to apply deep learning techniques such as momentum and data argumentation after taking this course.
Object recognition, Convolutional neural network (CNN), Deep learning, PyTorch
✔ Specialist skills | ✔ Intercultural skills | Communication skills | Critical thinking skills | ✔ Practical and/or problem-solving skills |
This class is a kind of active learning. The instructor will give some information, but students are required to develop their PyTorch code.
Course schedule | Required learning | |
---|---|---|
Class 1 | Introduction | Introduction |
Class 2 | Example of image classification | Example of image classification |
Class 3 | Gradient decent approach | Gradient decent approach |
Class 4 | Loss function | Loss function |
Class 5 | Overfitting | Overfitting |
Class 6 | Feature extraction and transfer learning | Feature extraction and transfer learning |
Class 7 | Classification methods | Classification methods |
Class 8 | Applications | Applications |
This class is a kind of active learning. The instructor will give some information, but students are required to develop their PyTorch code.
None. Please google by related keywords.
None. Please google by related keywords.
Assignments and report
Students need to implement the PyTorch code by themselves.
Students who took the course of Image Recognition (#SCE.I501) cannot take this course.