From Linear Algebra to Machine Learning

סקירה כללית

Explore the mathematical foundations of machine learning, from linear algebra to optimization, with practical Python implementations using NumPy, SciPy, and TensorFlow.

סילבוס

• Introduction to Linear Algebra
Vectors and Matrices
Matrix Operations and Properties
Determinants and Inverse Matrices
Eigenvalues and Eigenvectors
Practical Implementation with NumPy
• Linear Algebra in Machine Learning
Linear Transformations
Principal Component Analysis (PCA)
Singular Value Decomposition (SVD)
• Introduction to Optimization
Gradient Descent and Its Variants
Convex vs. Non-Convex Optimization
Practical Implementation with SciPy
• Probability and Statistics in Machine Learning
Probability Distributions and Properties
Bayes' Theorem and Applications
Linear Regression: Theory and Practice
• Fundamentals of Machine Learning
Decision Trees and Random Forests
Support Vector Machines (SVM)
Neural Networks and Deep Learning
• Introduction to TensorFlow
TensorFlow Basics and Computational Graphs
Building and Training a Feedforward Neural Network
Implementing CNNs and RNNs in TensorFlow
• Advanced Topics
Regularization Techniques: L1, L2, and Dropout
Hyperparameter Tuning and Model Selection
Introduction to Transfer Learning and Pre-trained Models
• Final Project
Define and Implement a Machine Learning Model
Demonstrate Understanding of Linear Algebra Applications
Present Results and Reflect on Learning

---

נושאים

Conference Talks