Qdrant is a vector database and vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more! Implement a unique custom modification of the HNSW algorithm for Approximate Nearest Neighbor Search. Support additional payload associated with vectors. Not only stores payload but also allows filter results based on payload values.Unlike Elasticsearch post-filtering, Qdrant guarantees all relevant vectors are retrieved.

Github: https://github.com/qdrant/qdrant

PyCameraServer is a Flask video / image / Youtube / IP Camera frames online web-editor with live streaming preview for objects recognition, extraction, segmentation, resolution upscaling, styling, colorization, interpolation, using OpenCV with neural network models: YOLO, Mask R-CNN, Caffe, DAIN, EDSR, LapSRN, FSRCNN, ESRGAN.

CUDA enabled.

The description's kind of weird, but it seems to use a neural network to generate pictures of someone based upon a picture that you give it. "Generate your lover with your photo," whatever that means.

An AI assisted online translation service, positioned as an alternative and rival to Google Translate. Translate text online, from a desktop application, or using their API (which has a separate billing plan - $5.56 per month, plus 1 cent per 500 characters). Supports 72 possible pairs of languages, with more being added. The basic account is about $10us per month (annual subscriptions are somewhat less per month, aggregate).

Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides state-of-the-art general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between TensorFlow 2.0 and PyTorch.

A basic server which implements a neural network and a REST API. Give it some basic training data, and then chat with it. It will slowly learn how to communicate with you.

Google has opened the source to DeepDream, the neural network image analysis application that made a splash by generating its own images. Here it is, and it tells you what the dependencies are.

CellF is the world’s first neural synthesiser. Its “brain” is made of biological neural networks that grow in a Petri dish and controls in real time it’s “body” that is made of an array of analogue modular synthesizers that work in synergy with it and play with human musicians. It is a completely autonomous instrument that consists of a neural network that is bio-engineered from my own cells that control a custom-built synthesizer. There is no programming or computers involved, only biological matter and analogue circuits; a ‘wet-analogue’ instrument.

The github repository for NuPIC Studio, which is an interactive desktop application for building HTM neuralnetworks, train them, collecting metrics, and exporting them to share. It also allows you to debug and experiment with those neural networks in a desktop environment. Built on top of the Python NuPIC library. Relies upon the Python modules you'd expect. IDE

A neuralnetwork written in javascript that runs in your browser. Meant for you to tinker with.