Directory
視頻
Курс: Advanced Machine Learning and Signal Processing. Чтобы вернуться, нажмите здесь.
- A warm welcome
- Linear algebra
- High Dimensional Vector Spaces
- Supervised vs. Unsupervised Machine Learning
- How ML Pipelines work
- Introduction to SparkML
- What is SystemML (1/2) ?
- What is SystemML (2/2) ?
- How to use Apache SystemML in IBM Watson Studio
- Extract - Transform - Load
- Linear Regression
- LinearRegression with Apache SparkML
- Linear Regression using Apache SystemML
- Batch Gradient Descent using Apache SystemML
- The importance of validation data to prevent overfitting
- Important evaluation measures
- Logistic Regression
- LogisticRegression with Apache SparkML
- Probabilities refresher
- Rules of probability and Bayes' theorem
- The Gaussian distribution
- Bayesian inference
- Bayesian inference - example
- Maximum a posteriori estimation
- Bayesian inference in Python
- Why is Naive Bayes "naive"
- Support Vector Machines
- Support Vector Machines using Apache SparkML
- Crossvalidation
- Hyper-parameter tuning using GridSearch
- Decision Trees
- Bootstrap Aggregation (Bagging) and RandomForest
- Boosting and Gradient Boosted Trees
- Gradient Boosted Trees with Apache SparkML
- Hyperparameter-Tuning using GridSeach and CrossValidation in Apache SparkML on Gradient Boosted Trees
- Regularization
- Introduction to Unsupervised Machine Learning
- Introduction to Clustering: k-Means
- Hierarchical Clustering
- Density-based clustering (Guest Lecture Saeed Aghabozorgi)
- Using K-Means in Apache SparkML
- Curse of Dimensionality
- Dimensionality Reduction
- Principal Component Analysis
- Principal Component Analysis (demo)
- Covariance matrix and direction of greatest variance
- Eigenvectors and eigenvalues
- Projecting the data
- PCA in SystemML
- Signal decomposition, time and frequency domains
- Fourier Transform in action
- Signal generation and phase shift
- The maths behind Fourier Transform
- Discrete Fourier Transform
- Fourier Transform in SystemML
- Fast Fourier Transform
- Nonstationary signals
- Scaleograms
- Continous Wavelet Transform
- Scaling and translation
- Wavelets and Machine Learning
- Wavelets transform and SVM demo