AiLearning-Theory-Applying
Get started with Ai theory and application practice quickly: Basic knowledge, Machine Learning, DeepLearning 2, Natural Language Processing BERT, and is constantly being updated. It contains a large number of comments and data sets, and strives to understand and reproduce each one.
Study chapter:
- Essential Mathematics Basic Knowledge
- Basics of Advanced Mathematics
- Calculus
- Taylor formula
- Linear algebra foundation
- random variable
- The basis of probability theory
- Several distributions of data science
- Kernel function
- Entropy and activation functions
- Regression analysis
- Hypothesis test
- Related Analysis
- Analysis of variance
- KMEANS Algorithm
- Bayesian Analysis
- Transformer that everyone can understand
- Chapter 1 - Transformer Network Architecture
- Chapter 2 - Text Vectorization
- Chapter 3 - Position Code
- Chapter 4 - Multiplication of multiplication of bullish attention mechanism -
- Chapter 5—Bulle Attention Mechanism—Full Process
- Chapter 6—Numerical Scaling
- Chapter 7—Feedforward Neural Network
- Chapter 8 - The Final Output
- Machine Learning
- Credit card fraud detection (including data sets)
- Industrial chemical production forecast (including data sets)
- Smart City-Road Passage Time Forecast (including Data Set)
- Building energy utilization forecast (including data set)
- Indoor Location & Navigation (dataset in kaggle)
- The 3rd Alibaba Cloud Panjiu Zhiwei Algorithm Competition (data set in Tianchi)
- Small project of practical machine learning (including data sets)
- Beginner of DeepLearning
- Necessary knowledge points for deep learning
- Entering the world neural network model of deep learning
- Convolutional neural network
- Recurrent neural network and word vector principle understanding
- LSTM network architecture and sentiment analysis application examples
- Kuaishou user active prediction (including data set)
- ACM SIGSPATIAL 2021 estimated arrival time (including data set)
- NLP general framework BERT project practice
- NLP general framework BERT principle understanding reading
- BERT source code interpretation and application examples
- Practical Chinese sentiment analysis based on BERT.md
- Principles and derivation of machine learning algorithms
- Li Hang—Statistical Learning Methods
- Li Hongyi—Abnormal detection
illustrate
This topic is not for commercial purposes. Please indicate the address of this topic when reprinting. If there is any infringement, please be sure to notify the author by email.
If there are any missing or errors in text, code, etc., I hope you will give me some advice and I am very grateful.
Email: [email protected]
License
Please refer to LICENSE for permission to use this article
