| 1일차 : 8월 28일(월) |
| 10:00 - 12:00 | 선형대수의 기초 | 이수찬 (국민대) |
| 개요: Data and matrices, matrix multiplication, rank-1 and low-rank matrices and Eckart-Young, Eigen-decomposition and SVD, symmetric/orthogonal matrices and the Spectral theorem |
| 12:00–13:00 | 중식 |
| 13:00–15:00 | 벡터 미적분학의 기초 | 이수찬 (국민대) |
| 개요: Matrix calculus and gradient, Hessian, Jacobian, backpropagation, positive-definite matrices and their definition, quadratic equations and convexity, multivariate Taylor series |
| 15:00–17:00 | 최적화의 기초 - 1 | 이수찬 (국민대) |
| 개요: Projection and least squares, Gradient descent, Newton’s method, Levenberg-Marquardt method, stochastic gradient descent, norms and optimization characteristics |
| 2일차 : 8월 29일(화) |
| 10:00–12:00 | 확률 변수와 확률 분포의 기초 | 이수찬 (국민대) |
| 개요: Joint probability, conditional probability, Bayes theorem and chain rule, covariance and correlation, univariate and multivariate Gaussian distributions, Gaussian mixture models, Markov chain |
| 12:00–13:00 | 중식 |
| 13:00–16:00 | 통계, 추정, 및 정보이론의 기초 | 이수찬 (국민대) |
| 개요: Maximum likelihood estimation, empirical risk minimization, regularization, Bayesian statistics and MAP estimation, entropy, KL divergence, mutual information |
| 16:00-17:00 | 최적화의 기초 - 2 | 이수찬 (국민대) |
| 개요: Constrained optimization problem, Lagrange multipliers, linear programming, quadratic programming |
