Machine-Learning-Study

Coursera - Machine Learning

1. Supervised Machine Learning : Regression and Classification

1 Week-Contents

• Machine Learning
• Learning Algorithm types
• Linear Regression Model
• Cost Function
• Gradient descent Algorithm

2 Week-Contents

• Feedback
  • Loss function
  • MSE
  • RMSE
• Multiple Linear Regression
• Vectorization
• Gradient descent for MLR
• Classification
• Logistic Regression
• Regularization

2. Advanced Learning Algorithms

3 Week-Contents

• Feedback
  • implementation of MSE
  • implementation of RMSE
  • overfitting solutions
  • L1, L2 regularization
• Neural Networks
  • Layers
  • Forward Propagation
• Perceptron
  • single-layer perceptron
  • multi-layer perceptron
• Tensorflow

4 Week-Contents

• Activation Functions
  • Sigmoid function
  • ReLU function
  • ELU function
  • softmax function
• Multiclass Classification
  • Loss function of Multiclass Classification
• Back Propagation

5 Week-Contents

• Feedback
  • Activation Functions
  • Binary step function
  • Linear activation function
  • Non-linear activation function
• Evaluating a model
• Bias and Variance
• Precision and Recall
  • Trading off percision and recall
• Decision tree
  • Pruning and Ensemble Methods
  • Impurity
• Random forest

6 Week-Contents

• Feedback
• Unsupervised Learning
  • Clustering
• K-means algorithm
  • algorithm process
  • Hierarchical Clustering
  • Elbow-method
• Gaussian distribution
• Anomaly detective algorithm
  • One-Class SVM
  • Isolation Forest
  • Autoencoder