Haobin Tan
Haobin Tan
๐ Posts
๐ค AI
Machine Learning
Deep Learning
Computer Vision
Natural Language Processing
PyTorch
๐งโ๐ป Coding
Python
Docker
Linux
Git
๐ป CS
Algorithm
Software Engineering
Project Management
Practical Skills
๐ Notes
GIE
Rechnerstruktur
Telematics
MMWAB
Thesis
Jobs
SI
๐จโ๐ซ Online Courses
AWS ML Engineer Program
๐งพ Rรฉsumรฉ
Light
Dark
Automatic
Deep Learning
Deep Learning (DL)
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning.
Haobin Tan
Last updated on Mar 31, 2022
Deep Learning
PyTorch
PyTorch is an open source machine learning framework that accelerates the path from research prototyping to production deployment.
Haobin Tan
Last updated on Mar 31, 2022
Deep Learning
๐ฅ Getting Started
Get your hands dirty on PyTorch quickly.
Haobin Tan
Last updated on Mar 27, 2022
Deep Learning
Neural Network Basics
Haobin Tan
Last updated on Mar 28, 2022
Deep Learning
Tensor
A specialized data structure that are very similar to arrays and matrices. In PyTorch, tensors are used to encode the inputs and outputs of a model, as well as the modelโs parameters.
Haobin Tan
Last updated on Mar 27, 2022
Deep Learning
Perceptron
Structure A perceptron is a single-layer neural network used for supervised learning of binary classifiers Perceptron $$ g(x) = \underbrace{\sum_{i=0}^n w_i x_i}_{\text{linear separator}} + \underbrace{w_0}_{\text{offset/bias}} $$
Haobin Tan
Last updated on Apr 3, 2022
Deep Learning
Autograd
A PyTorch a built-in differentiation engine that supports automatic computation of gradient for any computational graph.
Haobin Tan
Last updated on Mar 27, 2022
Deep Learning
๐ Activation Functions
Activation functions should be non-linear differentiable (since training with Backpropagation) Q: Why canโt the mapping between layers be linear? A: Compositions of linear functions is still linear, whole network collapses to regression.
Haobin Tan
Last updated on Apr 3, 2022
Deep Learning
Build and Train a Neural Network
A simple yet typical workflow of building and traing a neural network using PyTorch
Haobin Tan
Last updated on Mar 27, 2022
Deep Learning
๐ Loss Functions
Quantifies what it means to have a โgoodโ model Different types of loss functions for different tasks, such as: Classification Regression Metric Learning Reinforcement Learning Classification Classification: Predicting a discrete class label
Haobin Tan
Last updated on Apr 3, 2022
Deep Learning
»
Cite
×