The neural network was trained to simulate the olfactory system of a fruit fly

20 October 2021

The neural network was trained to simulate the olfactory system of a fruit fly

Scientists have created a three-layer neural network that classifies odors. After training, the model of communication between neurons accurately reproduced the structure of the olfactory system of a fruit fly.…

ORBIT: Microsoft dataset of images of household items

20 October 2021

ORBIT: Microsoft dataset of images of household items

ORBIT is a Microsoft dataset for training models to recognize objects from multiple images. ORBIT includes from 1 to 10 videos of 468 objects from everyday life. Usually object recognition…

SaLinA: FAIR library for developing models of sequential decision making

19 October 2021

SaLinA: FAIR library for developing models of sequential decision making

FAIR introduced SaLinA, a framework for developing models of sequential decision-making. Possible applications include reinforcement learning, computer vision, natural language processing. SaLinA’s idea is to make the implementation of sequential…

Neural network trained to predict accidents on the roads

17 October 2021

Neural network trained to predict accidents on the roads

A neural network trained on historical data and satellite images predicts the probability of an accident on certain sections of the road with ultra-high resolution. The model is planned to…

MT-NLG: generative language model of Microsoft and NVIDIA

16 October 2021

MT-NLG: generative language model of Microsoft and NVIDIA

The MT-NLG language model developed by Microsoft and NVIDIA has 530 billion parameters, which is 3 times more than that of GPT-3. MT-NLG consists of 105 layers and surpasses all…

Ego4D: FAIR dataset for teaching models egocentric perception

16 October 2021

Ego4D: FAIR dataset for teaching models egocentric perception

FAIR presented Ego4D — a dataset with videos shot in the first person. The dataset is aimed at teaching computer vision systems to perceive actions in a similar way as…

Google implements the MUM neural network in search

13 October 2021

Google implements the MUM neural network in search

Google has announced new features of its search engine based on the MUM neural network, which will become available in the near future. In particular, the search results page will…

Neural network has built a complete 3D map of a biological cell

9 October 2021

Neural network has built a complete 3D map of a biological cell

With the help of a convolutional neural network, scientists for the first time managed to carry out a complete 3D reconstruction of a biological cell based on electron microscopy data.…

Fake It Till You Make It: Microsoft synthetic face images dataset

9 October 2021

Fake It Till You Make It: Microsoft synthetic face images dataset

Microsoft has introduced a dataset of synthetic facial images Fake It Till You Make It. The dataset is aimed at pre-training facial recognition algorithms before being used in real-world scenarios.…

Google algorithms optimize traffic lights at intersections

7 October 2021

Google algorithms optimize traffic lights at intersections

Google is negotiating with cities around the world to implement algorithms to optimize the operation of traffic lights at intersections. The project is aimed at reducing the number of traffic…

Neural network trained to generate makeup to bypass facial recognition systems

4 October 2021

Neural network trained to generate makeup to bypass facial recognition systems

Israeli researchers have presented a model that generates makeup to bypass facial recognition systems. After applying cosmetics in accordance with the patterns presented by the neural network, the faces of…

DGM: DeepMind model for short-term weather forecasts

4 October 2021

DGM: DeepMind model for short-term weather forecasts

DeepMind has introduced a generative-adversarial DGMR network for weather prediction. DGMR has the highest accuracy of short-term forecasts among similar models. Rain forecasting is crucial for many industries, including aviation…

Minijack: FAIR benchmark for Reinforcement Learning algorithms

4 October 2021

Minijack: FAIR benchmark for Reinforcement Learning algorithms

FAIR has developed MiniHack, an open-source framework for evaluating reinforcement learning algorithms. With the help of MiniHack, you can study such characteristics of agents as learning, memory and credit assignment.…

The Open AI model generates short retellings of books

28 September 2021

The Open AI model generates short retellings of books

OpenAI has trained a neural network to retell the contents of books. The model is based on GPT-3 and uses the method of recursive decomposition, that is, first creates retellings…

FAIR has opened access to the Dynabench model evaluation platform

27 September 2021

FAIR has opened access to the Dynabench model evaluation platform

FAIR has opened access to Dynabench , a free platform for benchmarking models, to everyone. The functionality of the service allows you to evaluate the bias, accuracy and resource intensity…

American schools use text analysis to combat psychological violence

24 September 2021

American schools use text analysis to combat psychological violence

According to a report by the Center for Democracy and Technology, more than 70% of American schools use software to detect signs of bullying, violence and self-harm among schoolchildren. Most…

IC-GAN: generating synthetic images without training individual objects

21 September 2021

IC-GAN: generating synthetic images without training individual objects

IC-GAN is a set of FAIR models for generating images, objects and scenes on which were absent in the training dataset. IC-GAN can be used for data augmentation. Generative-adversarial networks…

Machine learning was used to analyze career growth

20 September 2021

Machine learning was used to analyze career growth

The researchers used neural networks to study periods of high activity of artists, scientists and directors. The obtained results can be used to identify and develop talented teenagers in various…

AIMI: database of medical image datasets

20 September 2021

AIMI: database of medical image datasets

The University of Cambridge has teamed up with Microsoft AI to develop the largest open-source medical image dataset platform, AIMI. AIMI already has more than 1 million images, and this…

Neural network trained to recognize Alzheimer’s disease with record accuracy

20 September 2021

Neural network trained to recognize Alzheimer’s disease with record accuracy

The researchers reported on the development of a method for early diagnosis of Alzheimer’s disease from fMRI images based on ResNet 18. The accuracy of the model is 99.99%, which…

SETI Project: application of machine learning for animal speech recognition

20 September 2021

SETI Project: application of machine learning for animal speech recognition

The CETI collaboration uses machine learning models to decipher the ways sperm whales communicate. The team includes dozens of scientists, including experts in the field of natural language processing, marine…