Notes for Deep Learning Specialization Courses led by Andrew Ng.

Developer Version of the R package CAST: Caret Applications for Spatio-Temporal models

TensorFlow in Practice Specialization. Join our Deep Learning Adventures community 🎉 and become an expert in Deep Learning, TensorFlow, Computer Vision, Convolutional Neural Networks, Kaggle Challenges, Data Augmentation and Dropouts Transfer Learning, Multiclass Classifications and Overfitting and Natural Language Processing NLP as well as Time…

All exercises for the course Elements of AI - Building AI

[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training

A new test set for ImageNet

Machine Learning to predict share prices in the Oil & Gas Industry

**Supervised-Learning** (with some Kaggle winning solutions and their reason of Model Selection for the given dataset).

Machine-Learning-Regression

It is from Kaggle Competitions where the training dataset is very small and the testing dataset is very large and we have to avoid or reduce overfiting by looking for best possible ways to overcome the most popular problem faced in field of predictive analytics.

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. arXiv:2307.09218.

PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.

Decision Tree classifier from scratch without any machine learning libraries

[ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chang, Zhangyang Wang

JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"

Deep Learning Adventures. Join our Deep Learning Adventures community 🎉 and become an expert in Deep Learning, TensorFlow, Computer Vision, Convolutional Neural Networks, Kaggle Challenges, Data Augmentation and Dropouts Transfer Learning, Multiclass Classifications and Overfitting and Natural Language Processing NLP as well as Time Series Forec…

Simple Demo to show how L2 Regularization avoids overfitting in Deep Learning/Neural Networks

Tuning GBMs (hyperparameter tuning) and impact on out-of-sample predictions

Pytorch implementation of the paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", along with three new modules to address overfitting issues found in the baseline model, and their ablation studies.

A study on the following problems: what the memorization problem is in meta-learning; why memorization problem happens; and how we can prevent it. (ICLR 2020)