DVD-GAN: Deepmind’s New Model Generates Realistic Videos

18 July 2019

DVD-GAN: Deepmind’s New Model Generates Realistic Videos

Researchers from Google Deepmind have proposed a novel method for efficiently generating videos using a deep neural network. In their paper, named “Efficient Video Generation on Complex Datasets”, researchers led…

BigGAN + BiGAN = BigBiGAN: New State-of-the art Model In Representation Learning

14 July 2019

BigGAN + BiGAN = BigBiGAN: New State-of-the art Model In Representation Learning

In the past years, Generative Adversarial Networks (or GANs) have shown unprecedented performance on tasks such as image generation. In a novel paper, researchers from Google Deepmind proposed a novel…

Robot Uses Machine Learning to Harvest Lettuce

14 July 2019

Robot Uses Machine Learning to Harvest Lettuce

The ‘Vegebot’ – a vegetable-picking robot that uses machine learning to harvest lettuce was developed by researchers from the University of Cambridge. The new robot shows that machine learning can…

GAN Network Can Do Lip Reading And Output Speech

7 July 2019

GAN Network Can Do Lip Reading And Output Speech

Researchers from Imperial College London and the Samsung AI Centre have proposed a method for visual speech recognition that can perform lipreading and synthesize audio out from the signal. To…

Researchers Created World’s First AI Universe Simulator

7 July 2019

Researchers Created World’s First AI Universe Simulator

A group of researchers from the Flatiron Institute’s Center for Computational Astrophysics has developed the world’s first deep learning-based 3D simulation of the universe. For the purpose of getting a…

Neural Network Identifies Emotions from The Way of Walking

5 July 2019

Neural Network Identifies Emotions from The Way of Walking

A group of researchers from the University of North Carolina and the University of Maryland has developed a method for identifying emotions from people’s walking style. The method, based on…

Researchers Use Machine Learning To Automatically Translate Long-Lost Languages

2 July 2019

Researchers Use Machine Learning To Automatically Translate Long-Lost Languages

A group of researchers from CSAIL at MIT and Google Brain used machine learning to automatically translate lost languages. The team developed a neural network-based system that can decipher texts…

Google Announced The Release of a New Dataset YouTube-8M Segments

30 June 2019

Google Announced The Release of a New Dataset YouTube-8M Segments

Google AI announced the release of a new dataset – YouTube-8M Segments. The novel dataset is an extension of the wide-known YouTube-8M dataset with human-verified labels on a subset of…

Google Maps Now Predicts Bus Delays With Machine Learning

28 June 2019

Google Maps Now Predicts Bus Delays With Machine Learning

Google announced the introduction of the new Google Maps feature – live traffic delay for busses, which uses machine learning to forecast bus delays in hundreds of cities across the…

STEAL: Novel State-of-the-art Method For Semantic Boundaries Prediction

26 June 2019

STEAL: Novel State-of-the-art Method For Semantic Boundaries Prediction

Researchers from NVIDIA have proposed a novel state-of-the-art method for learning semantic boundaries of objects in images. In their novel paper, “Devil is in the Edges: Learning Semantic Boundaries from…

Waymo Releases A Large Dataset For Autonomous Driving

25 June 2019

Waymo Releases A Large Dataset For Autonomous Driving

Waymo, the former Google self-driving project and one of the industry leaders in self-driving technology at the moment, is releasing a large public dataset for autonomous driving. As announced during…

Zoom to Learn, Learn to Zoom: Intel’s Deep Neural Network Improves 4X Computational Zoom

25 June 2019

Zoom to Learn, Learn to Zoom: Intel’s Deep Neural Network Improves 4X Computational Zoom

In a novel paper, researchers from UC Berkeley, HKUST and Intel Labs propose a deep learning based method that improves 4X computational zoom. In the past, many researchers have focused…

Researchers Propose A Neural Network That Accelerates MRI Reconstruction

21 June 2019

Researchers Propose A Neural Network That Accelerates MRI Reconstruction

Researchers from Facebook AI Research (FAIR), the University of Florida and NYU School of Medicine have proposed a neural network model that reduces uncertainty in MRI scans reconstruction. MRI reconstruction…

Inverse Cooking: Deep Neural Network Generates Recipes From Food Images

19 June 2019

Inverse Cooking: Deep Neural Network Generates Recipes From Food Images

Researchers from Universitat Politecnica de Catalunya and Facebook AI Research (FAIR) have proposed a method that given a food image generates the recipe as a sequence of instructions. Arguing that…

Replica: New Dataset of Highly Realistic 3D Indoor Scenes

17 June 2019

Replica: New Dataset of Highly Realistic 3D Indoor Scenes

A novel dataset of highly realistic 3D indoor scene reconstructions has been published and open-sourced by Facebook AI Research. The new dataset, called Replica Dataset contains 18 such indoor scene…

Researchers Join Forces To Tackle Climate Change with Machine Learning

16 June 2019

Researchers Join Forces To Tackle Climate Change with Machine Learning

A large group of eminent researchers from the world’s most prestigious universities and corporations such as Google, Microsoft, and DeepMind, have joined forces on a project to tackle climate change…

Adobe Trained A Neural Network That Detects Photoshopped Faces

15 June 2019

Adobe Trained A Neural Network That Detects Photoshopped Faces

Researchers from Adobe Research and the University of California Berkeley, have developed a method that can detect photoshopped faces by scripting photoshop. In the past few years, Adobe Research has…

Facebook Launched PyTorch Hub – A Central Place for PyTorch Models

15 June 2019

Facebook Launched PyTorch Hub – A Central Place for PyTorch Models

Facebook launched PyTorch Hub – a place where researchers and developers can upload and use pre-trained models. The novelty comes as part of Facebook’s plan to bring PyTorch closer to…

MIT Researchers Show How Single Classifier Can Solve Multiple Computer Vision Tasks

15 June 2019

MIT Researchers Show How Single Classifier Can Solve Multiple Computer Vision Tasks

Researchers from MIT have shown how a single classifier model can be used to tackle multiple different computer vision tasks. In their novel paper, researchers explore the potential of robust…

“How To Make A Pizza”: Researchers Design GAN Network That Can Create Pizza

13 June 2019

“How To Make A Pizza”: Researchers Design GAN Network That Can Create Pizza

In a novel paper, researchers from the Massachusetts Institute of Technology and the Qatar Computing Research Institute show how learning a compositional GAN model can be used to visually construct…

“Selfie”: Novel Method Improves Image Models Accuracy By Self-supervised Pretraining

11 June 2019

“Selfie”: Novel Method Improves Image Models Accuracy By Self-supervised Pretraining

Researchers from Google Brain have proposed a novel pre-training technique called Selfie, which applies the concept of masked language modeling to images. Arguing that language model pre-training and language modeling,…