bengsoon Goto Github PK

active_learning_sentiment_analysis

argilla

✨ Open-source tool for data-centric NLP. Argilla helps domain experts and data teams to build better NLP datasets in less time.

dedupe

:id: A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

dedupe-clustering-experiments

Experimenting new types of clustering algorithms for Dedupe library

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course

entity_resolution

fastbook

The fastai book, published as Jupyter Notebooks

fastcore

Python supercharged for the fastai library

fender

Image Classifier for Fender Guitars (Stratocaster, Telecaster, Jazzmaster) using fastai's neural network transfer learning (ResNet50 architecture)

google-research

Google Research

gradienttape

https://gradienttape.com/

gradienttape_archive

handling_imbalanced_data

Exploration into the techniques of handling imbalanced datasets for classifications

jupyterpy

Flexible API to convert Jupyter Notebook to Python file

lancedb

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

language_modeling_lotr

Language Modeling for Lord of The Rings

levenshtein_from_scratch_with_julia

Levenshtein Calculations from Scratch (used as an 'edit distance' in fuzzy string matching operations)

li_posts

Materials for LinkedIn Posts

machine-learning-competition-2020

SPWLA PDDA’s 1st Petrophysical Data-Driven Analytics Contest -- Sonic Log Synthesis

machine-learning-production-prediction

Machine Learning Models to predict daily oil production based on the platform parameters (well THPs, pipeline pressure etc)

machine_failure

mlops-zoomcamp

Personal Notes from MLOps Zoomcamp by DataTalks.club

model-zoo

Please do not feed the models

nbdev-test

nbdev_cards

Testing out nbdev

ner

nyt_topic_modeling

BERT-based Topic Modeling on New York Times Headlines (160k rows)

predictive-maintenance

Data Wrangling, EDA, Feature Engineering, Model Selection, Regression, Binary and Multi-class Classification (Python, scikit-learn)

setfit_breakdown

Breaking SetFit apart to help me get deeper understanding

sgd_scratch

- Exercise based on the Lesson 2 of fastai v1 DL course that explains the Stochastic Gradient Descent optimization method, which is commonly used in neural networks.