Complete Machine Learning Package Outline
Introduction to Python and Working with Data
- Python for Machine Learning
- Data Computations with NumPy
- Data Manipulation with Pandas
- Data Visualization with Matplotlib
- Data Visualization with Seaborn
- Data Visualization with Pandas
Data Analysis and Preparation
- Exploratory Data Analysis
- Data Preparation
- Categorical Feature Encoding
- Feature Scaling
- Handling Missing Values
Classical Machine Learning with Scikit-Learn
- Machine Learning Fundamentals
- Intro to Scikit-Learn
- Linear Models for Regression
- Linear Models for Classification
- SVMs for Regression
- SVM for Classification
- Decision Trees for Regression
- Decision Trees for Classification
- Random Forests for Regression
- Random Forests for Classification
- Ensemble Models
- Unsupervised learning with K-Means Clustering
- A Pracrical Introduction to Principal Component Analysis
Introduction to Deep Learning
- Intro to Articial Neural Networks
- Intro to TensorFlow for Artificial Neural Networks
- Neural Networks for Regression with TensorFlow
- Neural Networks for Classification with TensorFlow
Deep Computer Vision with TensorFlow
- Intro to Computer Vision with ConvNets
- ConvNets for Real World Data and Image Augmentation
- Transfer Learning with Pretrained Convolutional Neural Networks*
Natural Language Processing with TensorFlow
- Intro to NLP and Text Processing with TensorFlow
- Using Word Embeddings to Represent Texts
- Recurrent Neural Networks (RNNs)
- Using Convolutional Neural Networks for Texts Classification
- Using Pretrained BERT for Text Classification
Notes
*: The latest version of transfer learning and pretraining with ConvNets is available here.