Artificial Intelligence is a research area that aims at artificially creating intelligence like humans. In recent years, artificial intelligence was successfully applied to various domains with the advances on machine learning and deep learning utilizing big data and computation power. This lecture expects students to acquire knowledge that is essential for creating applications of artificial intelligence, explaining basic concepts and theories of artificial intelligence.
Students will be able to acquire knowledge that is essential for creating applications of artificial intelligence.
classification, regression, gradient-based method, perceptron, activation function, backpropagation, automatic differentiation, convolutional neural network
✔ Specialist skills | ✔ Intercultural skills | Communication skills | Critical thinking skills | ✔ Practical and/or problem-solving skills |
All classes are given in both Ookayama and Suzukakedai campuses with the use of video conference systems.
Course schedule | Required learning | |
---|---|---|
Class 1 | Class guidance | Artificial Intelligence applied to the real world |
Class 2 | Essential Mathematics for Machine Learning | Linear Algebra, Probability Theory and Statistics, Calculus |
Class 3 | Linear Regression | Loss function, empirical risk minimization, overfitting,regularization,bias and variance,linear model (regression),ridge regression |
Class 4 | Linear Classification | Linear model (classification),logistic regression, gradient methods |
Class 5 | Single-layer Neural Network | single-layer perceptron, activation functions, computational graph, automatic differentiation |
Class 6 | Multi-layer Neural Network | multi-layer perceptron, hidden units, backpropagation, softmax function |
Class 7 | Convolutional Neural Network | convolutional neural network, dropout |
Class 8 | Final examination |
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
Cource materials are distributed via OCW-i.
Based on the final exam.
Preferred to have basic knowledge about linear algebra, analysis, and mathematical statistics.