Machine Learning

To make machine learning and understand machine learning

17 Neural ODE

Published:
Summary: Neural ODE
Pages: 1

16 Adversarial Models

Published:
Summary: Adversarial models use a generator and discriminator
Pages: 3

15 Contrastive Models

Published:
Summary: Contrastive self-supervised learning models can utilize more data
Pages: 5

14 Generative Models

Published:
Summary: Generative self-supervised learning models can utilize more data
Pages: 5

14 Interpretability

Published:
Summary: Interpretability of models
Pages: 1

13 Energy-based Model

Published:
Summary: Energy-based model like Boltzmann machine is a special type of neural networks
Pages: 4

12 Classification

Published:
Summary:
Pages: 3

11 Unsupervised Learning

Published:
Tags:
Summary:
Pages: 3

10 Artificial Neural Networks

Published:
Summary: Artificial Neural Networks
Pages: 5

9 Ensemble Methods

Published:
Summary:

9 Tree-based Methods

Published:
Summary: Decision trees are a simple model for decision. Yet combined with other methods, decision trees can be quite powerful.
Pages: 3

8 Bayesian Methods

Published:
Summary: Machine learning based on bayesian statistics
Pages: 4

7 Embedding

Published:
Tags:
Summary: Embedding was one of the first ideas on computers and it is still the key component of machine learning
Pages: 2

6 Factorization

Published:
Summary: Factorization
Pages: 3

5 Linear Models

Published:
Summary: Linear models are very useful for baseline models.
Pages: 3

4 Machine Learning Performance

Published:
Summary: Benchmarking the performance of models
Pages: 1

3 Feature Engineering

Published:
Summary: In the industry, we spend a lot of time working on feature engineering.
Pages: 3

2 Machine Learning Basics

Published:
Summary: Some basics of machine learning
Pages: 3