开源软件名称（OpenSource Name）：

开源软件地址(OpenSource Url)：

开源编程语言(OpenSource Language)：

开源软件介绍(OpenSource Introduction)：

My Notes on Machine Learning

Machine Learning is a sub-field of artificial intelligence that uses data to train predictive models.

3 Types of machine learning

1. Supervised learning - Minimize an error function using labeled training data.
2. Unsupervised learning - Find patterns using unlabled training data. Examples include Principal component analysis and clustering.
3. Reinforcement learning - Maximize a reward. An agent interacts with an environment and learns to take action by maximizing a cumulative reward.

2 Types of machine learning problems

1. regression - predicting a continuous value attribute (Example: house prices)
2. classification - predicting a discrete value. (Example: pass or fail, hot dog/not hot dog)

Dimensionality reduction

Reducing number of features. A simple example is selecting the area of a house as a feature rather than using width and length seperately. Other examples include singular value decomposition, variational auto-encoders, and t-SNE (for visualizations), and max pooling layers for CNNs.

Machine learning models and applications

Neural Nets - A primer on neural networks. NNs are a suitable model for fixed input features and output labels.

Recurrent Neural Nets - A primer on recurrent neural networks. RNNs are a suitable model for sequences of information.

Deep Learning for NLP State of the art deep learning models and nlp applications such as sentiment analysis, translation and dialog generation.

Computer Vision

Convolutional Neural Networks CNNs basics. CNNS are suitable models for 2d grids of information such as computer vision problems.

• Image classification: res net, Inception v4, dense net
• Object detection: (with bounding boxes) yolo v4 (realtime object detection)
• Instance segmentation: mask r-cnn
• Semantic segmentation: U-Net

Advanced Topics

Transfer learning - storing knowledge gained while solving one problem and applying it to a different but related problem.

Neural architecture search - (a sub-field of automl) automatically designing neural networks architecture. NAS Survey / AutoML papers

NAS - google brain. reinforcement learning.
ENAS - google brain. effiicent nas.
PNAS
DARTS - differentiable
FB Net - differentiable
Squeeze NAS - NAS for image segmentation presentation

Microsoft lecture 12/18

Advanced Computer Vision Topics

Generative adversarial networks - GANs - 2 Neural networks compete against each other. The generative network generates candidates while the discriminative network evaluates them. This technique can generate realistic images. See GAN, Lap GAN, DC GAN, Big GAN, StyleGAN

Feature visualization - In computer vision, generating images representative of what neural networks are looking for.
TensorFlow Lucid, Activation Atlas

Feature attribution - In computer vision, determining and representing which pixels contribute to a classification. Example: Saliency maps, Deconvolution, CAM, Grad-CAM
tf explain - tensorflow visualization library.
fast ai heatmap - uses grad-cam