MChamith

AntiSpoofing

AWSTranscribeStreaming

using AWS transcribe streaming for transcibing audio

llm-course

Course with a roadmap and notebooks to get into Large Language Models (LLMs).

OCRL

Solutions for Optimal Control and reinforcement learning course assignments

RagProject

A simple RAG pipeline that enables semantic question-answering from PDF documents by combining vector embeddings and LLM-powered response generation.

RLExercises

Solutions for exercises in Reinforcement learning an Introduction book by Rich Sutton

SFCSimulation

Simulation for service function chain parititioninig based on multi agent reinforcement learning

Speaker_verification_gmm_ubm

speaker verification using gaussian mixture models

VPN_Pytorch

experiments on recreating value prediction network

MChamith/Speaker_verification_gmm_ubm

speaker verification using gaussian mixture models

MChamith/llm-course

Course with a roadmap and notebooks to get into Large Language Models (LLMs).

MChamith/OCRL

Solutions for Optimal Control and reinforcement learning course assignments

MChamith/AntiSpoofing

MChamith/Auto-PyTorch

Automatic architecture search and hyperparameter optimization for PyTorch

MChamith/AutomatedNASFL

MChamith/AWSTranscribeStreaming

using AWS transcribe streaming for transcibing audio

MChamith/hello_world

Test Repository

MChamith/RagProject

A simple RAG pipeline that enables semantic question-answering from PDF documents by combining vector embeddings and LLM-powered response generation.

MChamith/RLExercises

Solutions for exercises in Reinforcement learning an Introduction book by Rich Sutton

MChamith/S3Upload

For uploading face images to S3 which were extracted by processing .mov files and incorporated .face file to input facial area

MChamith/SFCSimulation

Simulation for service function chain parititioninig based on multi agent reinforcement learning

MChamith/SpatioAE

Spatio temporal 3D CNN autoencoder trained for unusual event detection

MChamith/SpoofDetection

Experiments done on developing face antispoofing

MChamith/VerticalFL

Experiments on Vertical Federated Learning

MChamith/VPN_Pytorch

experiments on recreating value prediction network

MChamith/aoe_project

Project utilising data from the Age of Empires api at 'https://aoestats.io'

MChamith/bertsekas-marl

PyTorch Implementation of the Sequential Multiagent Rollout algorithm

MChamith/DE_ZOOM_CAMP

MChamith/deploying-machine-learning-models

Code for the online course "Deployment of Machine Learning Models"

MChamith/FLASH-RL

FLASH-RL (Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning) is a novel and effective strategy for client selection in Federated Learning using Reinforcement Learning to address heterogeneity problems.

MChamith/IC3Net

Code for ICLR 2019 paper: Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

MChamith/MARL-Papers

Paper list of multi-agent reinforcement learning (MARL)

MChamith/NetworkPerformanceMonitor

MChamith/SampleForm

MChamith/serverless-delivery-framework

This is a boilerplate for version release pipeline with serverless framework

MChamith/value-prediction-network

NIPS 2017 Value Prediction Network

MChamith/VoiceDataCollector

MChamith/vuo-base-components

Base components for Vuo AI applications