Master fundamental AI concepts and develop practical machine learning skills in the beginner-friendly, 3-course program by AI visionary Andrew Ng.
I builded ML models with NumPy & scikit-learn, builded & trained supervised models for prediction & binary classification tasks (linear, logistic regression).
I applied practices for ML development & used unsupervised learning techniques for unsupervised learning including clustering & anomaly detection.
I builded & trained a neural network with TensorFlow to perform multi-class classification, & build & use decision trees & tree ensemble methods.
I builded recommender systems with a collaborative filtering approach & a content-based deep learning method & build a deep reinforcement learning model.
Course Link: Machine Learning Specialization
- Logistic Regression
- Artificial Neural Network
- Linear Regression
- Decision Trees
- Recommender Systems
- Supervised Machine Learning: Regression and Classification
- Introduction to Machine Learning
- Supervised vs Unsupervised Machine Learning
- Regression Model, Cost Function
- Gradient Descent
- Regression with Multiple Input Variables
- Multiple Linear Regression
- Gradient Descent in Practice
- Linear Regression
- Classification with Logistic Regression
- Sigmoid Function, Decision Boundry
- Cost Function for Logistic Regression
- Gradient Descent for Logistic Regression
- Overfitting
- Regularization
- Advanced Learning Algorithms
- Neural Networks
- Neurons and Layers
- Building Neural Network with TensorFlow
- Forward Propagation
- Vectorization
- Activation Function
- Multiclass Classification, Softmax
- Back Propagation
- Applying Machine Learning Model
- Model Evaluation and Selection
- Bias and Variance
- Loop of ML Development
- Skewed Datasets
- Decision Trees
- One-Hot Encoding
- Regression Trees
- Random Forest Algorithm
- XGBoost
- Tree Ensembles