Integrating Advanced CMA-ES Strategies into mlpack
Contributor: beny
This proposal seeks to enrich the mlpack library by incorporating advanced evolutionary strategies, specifically focusing on enhancing the Covariance...
Science and medicine
mlpack
a fast, flexible machine learning library
Technologies
C++
Topics
artificial intelligencedeep learningembeddedmachine learning
- Total projects
- 60
- Years participating
- 9
- Most recent
- 2024
Participation history
Historical projects
Implementing XGBoost
Contributor: Abhimanyu Dayal
The goal of this project is to finish the XGBoost implementation inside of mlpack, followed by intense tuning, profiling, and improving such that it...
Adding NSGA-3 and AGE-MOEA Multi Objective Optimizers
Contributor: Satyam Govind Shukla
Multi-objective optimization (MOO) plays a crucial role in decision-making across diverse fields, where conflicting objectives need to be balanced....
Performance and Memory Optimization for Machine Learning Algorithms in mlpack
Contributor: Mark Fischinger
In Google Summer of Code 2024, I focused on optimizing key algorithms in the mlpack library, targeting both performance and memory usage across...
ONNX-mlpack converter
Contributor: kumar utkarsh
Training intricate machine learning models to achieve the desired level of proficiency can be time-consuming and require high computational...
Implementing yolov3-tiny in mlpack
Contributor: Andrew Furey
I will implement the yolov3-tiny model using mlpack. I will get Darknet-19 working, flesh out the API, build and train yolov3-tiny, publish the...
Activation functions and Pooling methods
Contributor: Mayank Raj
Two new activation functions have been recently proposed FTSwish, and LiSHT and I am proposing to add them to mlpack along with two Pooling methods....
Enhance CMA-ES
Contributor: Suvarsh
Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is an evolutionary strategy which updates the covariance matrix of a normal search...
Expanding Reinforcement Learning in mlpack: DDPG and TD3 Agents Integration
Contributor: Tarek Elsayed
This project's primary objective was to enrich the mlpack reinforcement learning framework by incorporating new agents, specifically DDPG and TD3,...
Enhance CMA-ES from existing implementation in ensmallen - a optimization header library
Contributor: John Hoang
The project proposes to enhance the existing mlpack CMA-ES (Covariance matrix adaption-evolutionary strategy) implementation. From the outdated...
Ready to use Models
Contributor: Shubham Agrawal
The aim is to implement various pre-trained models ranging from very basic AlexNet to super complex networks, including implementing different layers...
Example Zoo
Contributor: Tarek Elsayed
Example Zoo is an implementation of mlpack showcasing its potential usage in the real-world domain. It will provide a better starting point for new...
Addition of PPO, Twin Delayed DDPG, Hindsight Experience Replay to RL Codebase
Contributor: Eshaan Agarwal
After comparing various algorithms and brainstorming about their methods of implementation, I came up with the Twin Delayed DDPG (TD3) Fujimoto et....
Replacing boost spirits
Contributor: Gopi Manohar Tatiraju
The project revolves around reducing the binary footprint of mlpack by replacing the functionality of boost::spirits to handle a more diverse range...
A Framework for Multiobjective Optimizers
Contributor: Nanubala Gnana Sai
The mlpack library boasts an extensive set of objective optimizers, almost all of which focus on single-objective problems. Previous works by Sayan...
Example Zoo
Contributor: Roshan Swain
Example Zoo is an implementation of mlpack showcasing its potential usage in the real-world domain. It will provide a better starting point for new...
Revamp mlpack bindings
Contributor: Nippun Sharma
The project proposes to revamp the existing mlpack bindings. Mlpack is one of the most flexible machine learning libraries when accessed through C++...
Improvisation and Implementation of ANN Modules
Contributor: Abhinav Anand
Adding new layers (Upsample, Group Normalization and ChannelShuffle) to the ANN module of mlpack. Improve the speed of pooling operations of max,...
Improve Tree Ensemble Support
Contributor: Rishabh Garg
Tree ensembles are arguably the best class of machine learning algorithms out there. They regularly win competitive data science competitions. This...
Ready to use Models in mlpack
Contributor: Aakash Kaushik
Is to implement MobileNetV1 which will also include implementing depthwise separable convolutions and a resnet model builder that can be used to...
Example Zoo
Contributor: David Port Louis
Example Zoo provides starters a glimpse of most if not all features provided by mlpack, such that users can run the code for themselves to see it in...
mlpack on RPi and other resource-constrained devices
Contributor: Omar Shrit
The objective of this project is to minimize mlpack library algorithms to fit into resource constrained devices such as Raspberry PI, Arduino, or...
Improvisation and Implementation of ANN Modules
Contributor: Anjishnu Mukherjee
In this project, my goal is to update the existing ANN facilities within mlpack and the deliverable is an improved ANN module. This includes adding...
Visualization Tool
Contributor: Jeffin Sam
Working with mlpack for almost a year was great. I have always been a fan of the concept see and do. If we can see a graph plotting the accuracy...
Application of ANN Algorithms Implemented in mlpack.
Contributor: Kartik Dutt
Over the course of the last couple of years, Computer Vision has played a crucial role in the field of Deep Learning. Object detection is one of the...
Implementing Essential Deep Learning Module
Contributor: Himanshu Pathak
In this project, I am trying to implement some deep learning modules which are used for classification. I am trying to implement some important...
Addition of Rainbow and Soft Actor-Critic to RL codebase
Contributor: Nishant Kumar
After comparing various algorithms and brainstorming about their methods of implementation, I came up with the Rainbow Hessel et al., 2017 and Soft...
Transformer and BERT in mlpack
Contributor: Mrityunjay Tripathi
Connecting the encoder and decoder through an attention mechanism has made some of the best translation models. The encoder encodes input sentences...
Automatically-Generated R Bindings
Contributor: Yashwant Singh Parihar
R is a programming language with a design focused on simplicity, effectiveness and performance, that is widely used in all kind of projects. With...
Application of ANN Algorithms Implemented in mlpack
Contributor: Mehul Kumar Nirala
Application of ANN algorithms implemented in mlpack. Implementation of VGG 19 for Image Classification. LSTM Networks for Sentiment Analysis. LSTM...
String Processing Utilities
Contributor: Jeffin Sam
To develop String Processing Utilities for boosting mlpack library to manipulate string data types and to convert it into numeric datatype to apply...
mlpack-Tensorflow Translator
Contributor: Sreenik Seal
The purpose of this project is to build a converter that can translate models built in Tensorflow, Keras, Pytorch, Mxnet, ONNX to mlpack's model...
Implementing Essential Deep Learning Modules
Contributor: Saksham Bansal
In recent years, generative adversarial networks have proven to be very effective for training generative models and hundreds of different variants...
Quantum Gaussian Mixture Models
Contributor: Sangyeon Kim
Gaussian Mixture Model (GMM) is widely used in computer vision as a state-of-the-art clustering algorithm. This project proposes Quantum Gaussian...
PPO(Proximal Policy Optimization)
Contributor: xiaohong ji
A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment,...
Implementing Essential Deep Learning Modules
Contributor: Toshal Agrawal
Various Deep learning architectures such as deep neural networks and recurrent neural networks are applied to fields including computer vision,...
NeuroEvolution of Augmenting Topologies & Multi-Objective Optimization
Contributor: Rahul Ganesh Prabhu
NeuroEvolution of Augmenting Toplogies (NEAT) is a genetic algorithm that can evolve networks of unbound complexity by starting from simple networks...
Advanced Kernel Density Estimation Improvements
Contributor: Roberto Hueso Gomez
Kernel Density Estimation (KDE) is a widely used non-parametric technique to estimate a probability density function. mlpack already had an...
LMNN (via Low-Rank optimization) & BoostMetric Implementation
Contributor: Manish Kumar
Many cognitive techniques, such as recognition and categorization are assumed to have need of establishing similarities between perceptual or...
Neural Collaborative Filtering
Contributor: Haritha Sreedharan Nair
Recommendation systems are widely used in various online and offline platforms, collaborative filtering being the most commonly used method for...
Alternatives to Neighborhood-Based Collaborative Filtering
Contributor: Wenhao Huang
The overall objective of this project is to improve the current CF module in mlpack to provide better rating prediciton, fast execution, and flexible...
Automated Binding Generator
Contributor: Yasmine Dumouchel
This automatically-generated Go binding proposal aims to allow Go users to have access to the fast and scalable machine learning library that is...
Variational Autoencoders
Contributor: Atharva Khandait
Variational Autoencoders(VAEs) are widely used in unsupervised learning of complicated distributions. The more classical generative models depend...
Implementing Essential Deep Learning Modules
Contributor: Shikhar Jaiswal
Over the years, Deep Learning has become a promising field of work, attracting attention from the most prominent Machine Learning researchers of the...
Neural Turing Machines
Contributor: Sumedh Ghaisas
One of the gems dug up by Deep Mind in the field of neural learning is Neural Turing Machines. By extending the capabilities of a simple neural...
Neural Evolution Algorithms on NES games
Contributor: KARTIK NIGHANIA
The goal of my project is to implement multiple neural evolution algorithms ie. ● NEAT - Neural Evolution through Augmented Topologies ● Hyper-NEAT -...
Deep Learning Modules
Contributor: Kris Singh
Implementation of RBM, ssRBM, GAN and stacked GAN
GSoC '17 "Augmented RNNs" project proposal
Contributor: Konstantin Sidorov
I am applying to work on the GSoC 2017 Augmented RNNs project. I am currently a first-year Software Engineering student from Astrakhan State...
Reinforcement Learning Framework
Contributor: Shangtong Zhang
This projects will implement a framework for double deep Q-Learning and some asynchronous methods for DeepRL including asynchronous one-step...
Cross-Validation and Hyper-Parameter Tuning
Contributor: Kirill Mishchenko
Solving a problem with machine learning algorithms is often a tedious process that requires many experiments before things start to work. The project...
GSoC-2017: Build testing with Docker and VMs
Contributor: Saurabh Gupta
The objectives of the project are as: Completing the build matrix - testing on different compilers, different architectures, different Boost...
Frank-Wolfe Algorithm for Sparse Optimization and Regularization of Atom Norms
Contributor: Chenzhe Diao
It is known in Jaggi's paper that the traditional OMP algorithm for sparse optimization problems could fit into FW type algorithm. This generalized...
Parallel stochastic optimization methods
Contributor: Shikhar Bhardwaj
The free lunch is over and with the ever increasing amounts of data to be analyzed and processed by learning algorithms, we need to find methods for...
Better Benchmarking for mlpack Libraries
Contributor: Dewang Sultania
There are many mlpack methods that have been added since the previous benchmarking system was build and they need to be benchmarked. These include...
We need to go deeper - GoogLeNet
Contributor: nilay_jain
To implement the components of the GoogLeNet architecture (the inception layer, global average pooling, and other pieces), and then build GoogLeNet...
Approximate Nearest Neighbor Search: Implementation of Multiprobe LSH and LSH Tuning
Contributor: mentekid
Approximate Nearest Neighbor Search solutions become appealing in problems where dimensionality increases. Locality Sensitive Hashing is a popular...
Neuroevolution Algorithms Implementation
Contributor: Bang
Neuroevolution algorithms search optimal solutions by evolution rather than learning, which enables them to deal with large complex problems. In this...
Approximate Nearest Neighbor Search
Contributor: Marcos Pividori
Mlpack provides an extensible, flexible exact nearest neighbor search implementation, with the ability to do dual-tree k-NN search. However, there is...
Dataset and Experimentation Tools
Contributor: KeonKim
This GSoC project aims to develop a tool for managing dataset and experimenting the data. This project is important because most of the time used...
R+ trees, Hilbert R trees, vantage point trees, random projection trees, UB trees implementation
Contributor: lozhnikov
Many methods of the mlpack machine learning library (such as nearest neighbor search, range search and others) are based on dual-tree algorithms...