There are 3 repositories under anns topic.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
EEG inverse solution with artificial neural networks. This package works with MNE-Python data structures for easy integration into your MNE-based M/EEG code
Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases superior to human experts.
A fast header-only graph-based index for approximate nearest neighbor search (ANNS). https://flatnav.net
Official implementation for paper "Navigating Labels and Vectors: A Unified Approach to Filtered Approximate Nearest Neighbor Search"
Simple gRPC server for vector searching implemented by Python and Faiss
Naive implementations of some ANNS (Approximate Nearest Neighbor Search) algorithms without any optimization and generalization.
The ultimate brain of Shotit, in charge of task coordination.
Four core workers of shotit: watcher, hasher, loader and searcher.
This repository contains materials and course projects during attending the Intelligent Systems Course, for more detailed information please have a look at my Final_Report files which have been separately uploaded for each of the projects and consist of all required information about the implementations, analyses, and anything else you may concern about that!
In this Repository, we intend to implement the DQN and also the DDQN algorithm in case of training an agent to solve the Lunar-Lander problem. there are lots of exciting results after training which have been attached.
The goal is to make an Artificial Neural Network that can predict, based on geo-demographical and transactional information given above, if any individual customer will leave the bank or stay (customer churn). Also, rank all the customers of the bank, based on their probability of leaving.
The frontend of shotit, with full documentation.
Media broker for serving video preview for shotit
Provide meta information and utility for shotit, for example, image proxy, cast and poster etc.
Sort the search results of Shotit to increase the correctness of Top1 result by using Keras and Faiss.
The front page to shotit.github.io
perceptron, backprop, RBF, SOM, hopfield nets, autoencoders (no external ML libs)
Data Mining Class @ The Open University
Discover the main building blocks of neural networks and understand the three main neural network architectures. Explore the process of solving a regression data problem