Towards Improved Meta-Learned Optimizers: Investigating the effect of L2-regularization on learned meta-optimizers. Research done for the AML course in Fall 2021/2022.

Version 2 of Reconstruction-Style

Slime Mold swarm optimization - efficient derivative free biologically inspired solver

Latent graphs (reward landscapes). Can humans learn them? How?

Image classification with very few data sample (n=25 per class)

Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)

🔧 Combine feature selectors with classifiers and regressors in a seamless pipeline using scikit-learn compatible meta-estimators for enhanced machine learning.

Experimenting with different ways of calculating metafeatures and embedding datasets

A repository that applies the Meta-SGD algorithm to High Energy Physics in Signal vs Background classification and studies the applicability of such methods.

XCS224U - Winter 2021 - Syed/Aiswarya - Intent Classification - Few Shot - Code and Dataset

Architecture search using unsupervised learning with symmetric auto-encoders and QLearning in PyTorch

Meta-Learning for Monitoring in Code Summarization Systems

Learning Dynamic Treatment Regime (DTR) via meta-learners

Comparitive work on dynamical identification that extends previous in-context learning based identification methods to different neural architectures.

The objective of this report is to conduct a study on the images of dogs and classify the emotions of each dog using deep learning algorithms, and to provide a new approach to solve this particular classification problem

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

This project investigates model editing techniques for Large Language Models (LLMs), focusing on how these models can be modified in specific domains without compromising overall performance.

I'm now interested in Learning to Adapt to Domain Shift

A project implementing better evaluation scenarios for community models for malicious content detection, and meta-learning GNNs to achieve better downstream adaptation.

A repository contains research papers related to RL, NLP, CV, ML, DL, Meta Learning, Incremental, etc.