Shu-Ren Chang's repositories
awesome-seml
A curated list of articles that cover the software engineering best practices for building machine learning applications.
Capstone_Project_Credit_Card_Fraud_Detetction
Credit Card Fraud Detetction Project By Shu-Ren Chang
Classifying-Skin-Cancer-Melanoma-using-Convolutional-Neural-Networks
Classifying Skin Cancer (Melanoma) using Convolutional Neural Networks
Cross-Validation-for-Linear-Regression-for-House-Prices
This notebook demonstrates how to do cross-validation (CV) for linear regression with `sklearn`. This technique is commonly used in almost all modelling in decision trees, SVM etc.
Hand-Gesture-Recognition-with-CNN-and-RNN
In this project, the task is to build a 3D Conv model that will be able to predict the 5 gestures correctly.
linux
Linux kernel source tree
MLOps-NLP-Case-Study-Architecture-Design-for-Development-and-Production-Environments
This case study, authored by Shu-Ren Chang, Ph.D. explores MLOps in the context of NLP analytics. It includes the design of an MLOps architecture tailored for both development and production environments.
NLP_Lexcial_Processing
The demoed Lexical Process in Natural Language Procession includes regular expressions, tokenization, stemming, lemmatization, TF-IDF model, phonetic hashing, and minimum edit distance algorithm.
NLP_Pipeline-Hugging-Face-offers-Transformer-library-API
Hugging Face offers the Transformer library API for NLP models. Pipelines are a great and easy way to use all types of models for inference. These pipelines offers a simple API dedicated to several tasks, including named entity recognition, masked language modelling, sentiment analysis, feature extraction, and question answering.
NLP_Semantic_Processing
Semantic processing is the most challenging area in the field of NLP because it is difficult to let machines understand the text the same way as human do such as inferring the intent, distinguishing ambiguity of words, dealing with synonyms, detecting sarcasm, etc.
NLP_Syntactic_Processing
Syntactic Processing techniques include: 1. PoS tagging and HMM model; 2. Constituency and Dependency parsing; 3. Name Entity Recognition (NER); 4. Custom NER and Conditional Random Fields (CRF); and 5. Application of each topic in Python using Spacy library.
NLP_Syntactic_Processing_for_Medical_Data_with_NER_CRF_using_SpaCy
This project aims to identify disease names along with treatment plans to help physicians arrange better treatments. The textual extraction technique: Name Entity Recognition (NER), CRF (Conditional Random Field) classifier, Random Forest Classifier, and HMM (Hidden Markov Model) are used to identify the entities like Disease and Treatment.
Regular_Expressions_Practice
Regular expressions are very powerful tool in text processing that help clean and handle textual analysis more efficiently.
Sentiment-Analysis-for-Movie_Reviews_using_Bernoulli_Naive_Bayes
A Multinomial Naive Bayes classification model was built and trained in Python to predict the accuracy.
UTF-8_Encoder-Decoder_for_String
This coding is used as encoder-decoder for string for UTF-8, UTF-16, and UTF-32 codes