Tagged | research
-
Accurate Alpha Matting for Portrait Mode Selfies on Pixel 6
(ai.googleblog.com) -
Resolving High-Energy Impacts on Quantum Processors
(ai.googleblog.com) -
Does Your Medical Image Classifier Know What It Doesn’t Know?
(ai.googleblog.com) -
Scientists Develop 3D Simulation of a Living Cell
(blogs.nvidia.com) -
GANcraft: Turning Gamers into 3D Artists
(developer.nvidia.com) -
Introducing StylEx: A New Approach for Visual Explanation of Classifiers
(ai.googleblog.com) -
Learning to Route by Task for Efficient Inference
(ai.googleblog.com) -
Scaling Vision with Sparse Mixture of Experts
(ai.googleblog.com) -
21st Century Cryptography – Asynchronous ASIC
(galois.com) -
Presentation: Moldable Development by Example
(www.infoq.com) -
NVIDIA AI: Generating Motion Capture Animation Without Hardware or Motion Data
(developer.nvidia.com) -
Improving the performance of large-scale applications via basic block reordering
(research.facebook.com) -
Interpretable Deep Learning for Time Series Forecasting
(ai.googleblog.com) -
Should It Be Easier to Trust Machines or Harder to Trust Humans?
(galois.com) -
General and Scalable Parallelization for Neural Networks
(ai.googleblog.com) -
Improving Vision Transformer Efficiency and Accuracy by Learning to Tokenize
(ai.googleblog.com) -
Deep Learning Detects Earthquakes at Millimeter-Scale
(developer.nvidia.com) -
RLDS: An Ecosystem to Generate, Share, and Use Datasets in Reinforcement Learning
(ai.googleblog.com) -
MURAL: Multimodal, Multi-task Retrieval Across Languages
(ai.googleblog.com) -
Predicting Text Selections with Federated Learning
(ai.googleblog.com) -
Predicting Text Readability from Scrolling Interactions
(ai.googleblog.com) -
RLiable: Towards Reliable Evaluation & Reporting in Reinforcement Learning
(ai.googleblog.com) -
MetNet-2: Deep Learning for 12-Hour Precipitation Forecasting
(ai.googleblog.com) -
Model Ensembles Are Faster Than You Think
(ai.googleblog.com) -
Improved On-Device ML on Pixel 6, with Neural Architecture Search
(ai.googleblog.com) -
Self-Supervised Reversibility-Aware Reinforcement Learning
(ai.googleblog.com) -
Grammar Correction as You Type, on Pixel 6
(ai.googleblog.com) -
Kangaroo: A new flash cache optimized for tiny objects
(engineering.fb.com) -
Deciding Which Tasks Should Train Together in Multi-Task Neural Networks
(ai.googleblog.com) -
Practical Differentially Private Clustering
(ai.googleblog.com) -
Predicting Spreadsheet Formulas from Semi-structured Contexts
(ai.googleblog.com) -
SimVLM: Simple Visual Language Model Pre-training with Weak Supervision
(ai.googleblog.com) -
How Underspecification Presents Challenges for Machine Learning
(ai.googleblog.com) -
An ML-based Framework for COVID-19 Epidemiology
(ai.googleblog.com) -
Self-Supervised Learning Advances Medical Image Classification
(ai.googleblog.com) -
Finding Complex Metal Oxides for Technology Advancement
(ai.googleblog.com) -
Introducing FLAN: More generalizable Language Models with Instruction Fine-Tuning
(ai.googleblog.com) -
FedJAX: Federated Learning Simulation with JAX
(ai.googleblog.com) -
Efficient Partitioning of Road Networks
(ai.googleblog.com) -
Improving Generalization in Reinforcement Learning using Policy Similarity Embeddings
(ai.googleblog.com) -
HE-MAN: The Homomorphic Encryption Mechanism for Approximating Noise
(galois.com) -
Implementing academic papers: lessons learned from Elasticsearch and Lucene
(www.elastic.co) -
Pathdreamer: A World Model for Indoor Navigation
(ai.googleblog.com) -
Revisiting Mask-Head Architectures for Novel Class Instance Segmentation
(ai.googleblog.com) -
Toward Fast and Accurate Neural Networks for Image Recognition
(ai.googleblog.com) -
Music Conditioned 3D Dance Generation with AIST++
(ai.googleblog.com) -
A Gentle Introduction to Graph Neural Networks
(distill.pub) -
Understanding Convolutions on Graphs
(distill.pub) -
Discovering Anomalous Data with Self-Supervised Learning
(ai.googleblog.com) -
Introducing Omnimattes: A New Approach to Matte Generation using Layered Neural Rendering
(ai.googleblog.com) -
Detecting Abnormal Chest X-rays using Deep Learning
(ai.googleblog.com) -
Recreating Natural Voices for People with Speech Impairments
(ai.googleblog.com) -
RAMP-TAO: Layering atomic transactions on Facebook’s online graph store
(engineering.fb.com) -
Flow Equivalence: A Step on the Path to Formally Verified Asynchronous Design
(galois.com) -
Demonstrating the Fundamentals of Quantum Error Correction
(ai.googleblog.com) -
SoundStream: An End-to-End Neural Audio Codec
(ai.googleblog.com) -
Risk-driven backbone management during COVID-19 and beyond
(engineering.fb.com) -
Deciphering Ancient Texts with AI
(developer.nvidia.com) -
When do recommender systems amplify user preferences? A theoretical framework and mitigation strategies
(research.fb.com) -
AI Detects Gravitational Waves Faster than Real Time
(developer.nvidia.com) -
Improved Detection of Elusive Polyps via Machine Learning
(ai.googleblog.com) -
Open sourcing Winterfell: A STARK prover and verifier
(engineering.fb.com) -
Display systems research: Reverse passthrough VR
(research.fb.com) -
A linear programming approach for optimizing features in ML models
(engineering.fb.com) -
Mapping Africa’s Buildings with Satellite Imagery
(ai.googleblog.com) -
Advances in TF-Ranking
(ai.googleblog.com) -
King’s College London Accelerates Synthetic Brain 3D Image Creation Using AI Models Powered by Cambridge-1 Supercomputer
(developer.nvidia.com) -
Graph Neural Networks as Neural Diffusion PDEs
(blog.twitter.com) -
Applying Advanced Speech Enhancement in Cochlear Implants
(ai.googleblog.com) -
High-dimensional Bayesian optimization with sparsity-inducing priors
(research.fb.com) -
Multi-task Prediction of Organ Dysfunction in ICUs
(ai.googleblog.com) -
Automating root cause analysis for infrastructure systems
(research.fb.com) -
Predicting Protein Structures with Deep Learning
(developer.nvidia.com) -
High Fidelity Image Generation Using Diffusion Models
(ai.googleblog.com) -
Transforming Brain Waves into Words with AI
(developer.nvidia.com) -
Speeding Up Reinforcement Learning with a New Physics Simulation Engine
(ai.googleblog.com) -
Why Asynchronous Design?
(galois.com) -
Optimizing model accuracy and latency using Bayesian multi-objective neural architecture search
(research.fb.com) -
From Vision to Language: Semi-supervised Learning in Action…at Scale
(ai.googleblog.com) -
Reducing the Computational Cost of Deep Reinforcement Learning Research
(ai.googleblog.com) -
Fighting Disease-Carrying Mosquitoes with Neural Networks
(developer.nvidia.com) -
Ribbon filter: Practically smaller than Bloom and Xor
(engineering.fb.com) -
Proof Repair and Code Generation
(galois.com)#dev-tools #programming-languages #research #formal-verification
-
NVIDIA Research: NeRF-Tex: Neural Reflectance Field Textures
(developer.nvidia.com) -
Quickly Training Game-Playing Agents with Machine Learning
(ai.googleblog.com) -
Achieving Precision in Quantum Material Simulations
(ai.googleblog.com) -
Improving Breast Cancer Detection in Ultrasound Imaging Using AI
(developer.nvidia.com) -
Improving Genomic Discovery with Machine Learning
(ai.googleblog.com) -
NVIDIA Research: Learning Modular Scene Representations With Neural Scene Graphs
(developer.nvidia.com) -
NVIDIA Research: An Unbiased Ray-Marching Transmittance Estimator
(developer.nvidia.com) -
Quantum Machine Learning and the Power of Data
(ai.googleblog.com) -
NVIDIA Research: An Analytic BRDF for Materials with Spherical Lambertian Scatterers
(developer.nvidia.com) -
NVIDIA Research: Appearance-Driven Automatic 3D Model Simplification
(developer.nvidia.com) -
NVIDIA Research: Learning and Rendering Dynamic Global Illumination with One Tiny Neural Network in Real-Time
(developer.nvidia.com) -
Let It Flow: AI Researchers Create Looping Videos From Still Images
(developer.nvidia.com) -
Learning an Accurate Physics Simulator via Adversarial Reinforcement Learning
(ai.googleblog.com) -
Harnessing second order optimizers from deep learning frameworks
(blog.twitter.com) -
Simple scalable graph neural networks
(blog.twitter.com) -
FRILL: On-Device Speech Representations using TensorFlow-Lite
(ai.googleblog.com) -
The Importance of A/B Testing in Robotics
(ai.googleblog.com) -
NVIDIA Research: Fast Uncertainty Quantification for Deep Object Pose Estimation
(developer.nvidia.com) -
Using Variational Transformer Networks to Automate Document Layout Design
(ai.googleblog.com) -
Data Cascades in Machine Learning
(ai.googleblog.com) -
Extending Contrastive Learning to the Supervised Setting
(ai.googleblog.com) -
Toward Generalized Sim-to-Real Transfer for Robot Learning
(ai.googleblog.com) -
A Browsable Petascale Reconstruction of the Human Cortex
(ai.googleblog.com) -
Increasing experimentation accuracy and speed by using control variates
(codeascraft.com) -
Provably expressive graph neural networks
(blog.twitter.com) -
Cross-Modal Contrastive Learning for Text-to-Image Generation
(ai.googleblog.com) -
Introducing Half-Double: New hammering technique for DRAM Rowhammer bug
(security.googleblog.com) -
Understanding Contextual Facial Expressions Across the Globe
(ai.googleblog.com) -
KELM: Integrating Knowledge Graphs with Language Model Pre-training Corpora
(ai.googleblog.com) -
Deep Learning Helps Demystify Authorship of a Dead Sea Scroll
(developer.nvidia.com) -
Cutting the curb: The power of accessibility research
(research.fb.com) -
Project Guideline: Enabling Those with Low Vision to Run Independently
(ai.googleblog.com) -
Learning to Manipulate Deformable Objects
(ai.googleblog.com) -
Running Border Gateway Protocol in large-scale data centers
(engineering.fb.com) -
ALIGN: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
(ai.googleblog.com) -
Accelerating Eye Movement Research for Wellness and Accessibility
(ai.googleblog.com) -
Adversarial Reprogramming of Neural Cellular Automata
(distill.pub) -
Crisscrossed Captions: Semantic Similarity for Images and Text
(ai.googleblog.com) -
Introducing FELIX: Flexible Text Editing Through Tagging and Insertion
(ai.googleblog.com) -
Do Wide and Deep Networks Learn the Same Things?
(ai.googleblog.com) -
ICLR Invited Talk on Geometric Deep Learning
(blog.twitter.com) -
Flexible, Scalable, Differentiable Simulation of Recommender Systems with RecSim NG
(ai.googleblog.com) -
Model-Based RL for Decentralized Multi-agent Navigation
(ai.googleblog.com) -
Holistic Video Scene Understanding with ViP-DeepLab
(ai.googleblog.com) -
Public Tech Talk: “Gillian Verification of JavaScript and C”
(galois.com)#programming-languages #research #cs-theory #formal-verification
-
HDR+ with Bracketing on Pixel Phones
(ai.googleblog.com) -
Evolving Reinforcement Learning Algorithms
(ai.googleblog.com) -
MaX-DeepLab: Dual-Path Transformers for End-to-End Panoptic Segmentation
(ai.googleblog.com) -
Cost-sensitive exploration in multi-armed bandits: Application to SMS routing
(research.fb.com) -
Multi-Task Robotic Reinforcement Learning at Scale
(ai.googleblog.com) -
Auto-placement of ad campaigns using multi-armed bandits
(research.fb.com) -
Introducing causal network motifs: A new approach to identifying heterogeneous spillover effects
(research.fb.com) -
Weight Banding
(distill.pub) -
Monster Mash: A Sketch-Based Tool for Casual 3D Modeling and Animation
(ai.googleblog.com) -
Branch Specialization
(distill.pub) -
The Dog Ate My Protocol Spec; A Demo
(galois.com) -
Constructing Transformers For Longer Sequences with Sparse Attention Methods
(ai.googleblog.com) -
Recursive Classification: Replacing Rewards with Examples in RL
(ai.googleblog.com) -
Using Neural Networks to Find Answers in Tables
(ai.googleblog.com) -
Detecting explicit content in songs
(deezer.io) -
Applying Machine Learning to…..Yeast?
(ai.googleblog.com) -
Optimizing Multiple Loss Functions with Loss-Conditional Training
(ai.googleblog.com) -
A Scalable Approach to Reducing Gender Bias in Google Translate
(ai.googleblog.com) -
Chip Design with Deep Reinforcement Learning
(ai.googleblog.com) -
Exploring Evolutionary Meta-Learning in Robotics
(ai.googleblog.com) -
Turbine: Facebook’s service management platform for stream processing
(engineering.fb.com) -
Off-Policy Estimation for Infinite-Horizon Reinforcement Learning
(ai.googleblog.com) -
EfficientDet: Towards Scalable and Efficient Object Detection
(ai.googleblog.com) -
An Optimistic Perspective on Offline Reinforcement Learning
(ai.googleblog.com) -
uDepth: Real-time 3D Depth Sensing on the Pixel 4
(ai.googleblog.com)#deep-learning #image-processing #hardware #sensors #research
-
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
(ai.googleblog.com) -
Advancing Self-Supervised and Semi-Supervised Learning with SimCLR
(ai.googleblog.com)#deep-learning #machine-learning #image-processing #research
-
Thread: Circuits
(distill.pub) -
Exploring Nature-Inspired Robot Agility
(ai.googleblog.com) -
Improving Audio Quality in Duo with WaveNetEQ
(ai.googleblog.com)#deep-learning #machine-learning #audio-processing #research
-
Presentation: Quantum Computing Deep Dive
(www.infoq.com) -
A Neural Weather Model for Eight-Hour Precipitation Forecasting
(ai.googleblog.com) -
Massively Scaling Reinforcement Learning with SEED RL
(ai.googleblog.com) -
Reducing the Carbon Foot Prints of CNNs at the cost of interactions-Depthwise & Pointwise Conv..
(towardsdatascience.com)#deep-learning #machine-learning #image-processing #research
-
Visual Transfer Learning for Robotic Manipulation
(ai.googleblog.com) -
Introducing Dreamer: Scalable Reinforcement Learning Using World Models
(ai.googleblog.com) -
Introducing Piranha: An Open Source Tool to Automatically Delete Stale Code
(eng.uber.com) -
Visualizing Neural Networks with the Grand Tour
(distill.pub) -
Soli Radar-Based Perception and Interaction in Pixel 4
(ai.googleblog.com)#signal-processing #machine-learning #mobile #hardware #research
-
Fast and Easy Infinitely Wide Networks with Neural Tangents
(ai.googleblog.com) -
Real-Time 3D Object Detection on Mobile Devices with MediaPipe
(ai.googleblog.com) -
Zoom In: An Introduction to Circuits
(distill.pub) -
More Efficient NLP Model Pre-training with ELECTRA
(ai.googleblog.com) -
Announcing TensorFlow Quantum: An Open Source Library for Quantum Machine Learning
(ai.googleblog.com) -
Measuring Compositional Generalization
(ai.googleblog.com) -
Toward Human-Centered Design for ML Frameworks
(ai.googleblog.com) -
Ultra-High Resolution Image Analysis with Mesh-TensorFlow
(ai.googleblog.com) -
Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer
(ai.googleblog.com) -
Setting Fairness Goals with the TensorFlow Constrained Optimization Library
(ai.googleblog.com) -
Generating Diverse Synthetic Medical Image Data for Training Machine Learning Models
(ai.googleblog.com) -
Presentation: Breakthroughs and the Future of (Deep) Reinforcement Learning
(www.infoq.com) -
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
(towardsdatascience.com) -
AutoFlip: An Open Source Framework for Intelligent Video Reframing
(ai.googleblog.com) -
Learning to See Transparent Objects
(ai.googleblog.com) -
TyDi QA: A Multilingual Question Answering Benchmark
(ai.googleblog.com) -
ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems
(ai.googleblog.com) -
PyKrylov: Accelerating Machine Learning Research at eBay
(tech.ebayinc.com) -
Encode, Tag and Realize: A Controllable and Efficient Approach for Text Generation
(ai.googleblog.com) -
Towards a Conversational Agent that Can Chat About…Anything
(ai.googleblog.com) -
Releasing the Drosophila Hemibrain Connectome — The Largest Synapse-Resolution Map of Brain Connectivity
(ai.googleblog.com) -
Reformer: The Efficient Transformer
(ai.googleblog.com) -
Visualizing the Impact of Feature Attribution Baselines
(distill.pub) -
Can You Trust Your Model’s Uncertainty?
(ai.googleblog.com) -
Simulating Quantum Circuits with Tensor Networks
(towardsdatascience.com) -
ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations
(ai.googleblog.com) -
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
(eng.uber.com) -
The On-Device Machine Learning Behind Recorder
(ai.googleblog.com) -
Improving Out-of-Distribution Detection in Machine Learning Models
(ai.googleblog.com) -
Protecting programmatic access to user data with Binary Authorization for Borg
(security.googleblog.com) -
Improvements to Portrait Mode on the Google Pixel 4 and Pixel 4 XL
(ai.googleblog.com) -
Lessons Learned from Developing ML for Healthcare
(ai.googleblog.com)#data-science #machine-learning #image-processing #research #biotech
-
Fairness Indicators: Scalable Infrastructure for Fair ML Systems
(ai.googleblog.com) -
Understanding Transfer Learning for Medical Imaging
(ai.googleblog.com)#data-science #machine-learning #image-processing #research #biotech
-
Controlling Text Generation with Plug and Play Language Models
(eng.uber.com) -
Developing Deep Learning Models for Chest X-rays with Adjudicated Image Labels
(ai.googleblog.com) -
EfficientDet: Scalable and Efficient Object Detection Review
(towardsdatascience.com) -
RecSim: A Configurable Simulation Platform for Recommender Systems
(ai.googleblog.com) -
SPICE: Self-Supervised Pitch Estimation
(ai.googleblog.com) -
New Insights into Human Mobility with Privacy Preserving Aggregation
(ai.googleblog.com) -
Introducing the Next Generation of On-Device Vision Models: MobileNetV3 and MobileNetEdgeTPU
(ai.googleblog.com)#machine-learning #image-processing #mobile #hardware #research
-
Quantum Supremacy Using a Programmable Superconducting Processor
(ai.googleblog.com)#hardware #research #quantum-computing #cs-theory #computation
-
On-Device Captioning with Live Caption
(ai.googleblog.com) -
Learning to Assemble and to Generalize from Self-Supervised Disassembly
(ai.googleblog.com) -
Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules
(ai.googleblog.com) -
The Visual Task Adaptation Benchmark
(ai.googleblog.com) -
Fast dimensional analysis for root cause analysis at scale
(engineering.fb.com) -
Detecting Stop Signs and Traffic Signals: Deep Learning at Lyft Mapping
(eng.lyft.com) -
Computing Receptive Fields of Convolutional Neural Networks
(distill.pub) -
Audio and Visual Quality Measurement using Fréchet Distance
(ai.googleblog.com)#data-science #algorithms #audio-processing #research #video-processing
-
Speeding up Deep Clustering with Concrete GMVAEs
(product.hubspot.com) -
Video Architecture Search
(ai.googleblog.com) -
Exploring Massively Multilingual, Massive Neural Machine Translation
(ai.googleblog.com) -
ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
(ai.googleblog.com) -
Improving Quantum Computation with Classical Machine Learning
(ai.googleblog.com) -
Automating Weak Supervision
(blog.fastforwardlabs.com) -
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
(ai.googleblog.com) -
The Paths Perspective on Value Learning
(distill.pub) -
Facebook Open-Sources RoBERTa: an Improved Natural Language Processing Model
(www.infoq.com) -
An Inside Look at Flood Forecasting
(ai.googleblog.com) -
Project Ihmehimmeli: Temporal Coding in Spiking Neural Networks
(ai.googleblog.com) -
Using Deep Learning to Inform Differential Diagnoses of Skin Diseases
(ai.googleblog.com) -
Learning Cross-Modal Temporal Representations from Unlabeled Videos
(ai.googleblog.com) -
Assessing the Quality of Long-Form Synthesized Speech
(ai.googleblog.com) -
Introducing Harmonia: Context-Aware Product Recommendation From Room Images
(tech.wayfair.com) -
Recursive Sketches for Modular Deep Learning
(ai.googleblog.com) -
Transfer Learning - from the ground up
(blog.fastforwardlabs.com) -
Transfer Learning from RGB to Multi-band Imagery
(www.azavea.com) -
Giving Lens New Reading Capabilities in Google Go
(ai.googleblog.com) -
Exploring Weight Agnostic Neural Networks
(ai.googleblog.com) -
Bi-Tempered Logistic Loss for Training Neural Nets with Noisy Data
(ai.googleblog.com) -
Advanced Topics in Neural Networks
(towardsdatascience.com) -
On-Device, Real-Time Hand Tracking with MediaPipe
(ai.googleblog.com) -
Turbo, An Improved Rainbow Colormap for Visualization
(ai.googleblog.com)#data-science #machine-learning #image-processing #visualisation #research
-
Joint Speech Recognition and Speaker Diarization via Sequence Transduction
(ai.googleblog.com) -
Labeling, transforming, and structuring training data sets for machine learning
(www.oreilly.com) -
Project Euphonia’s Personalized Speech Recognition for Non-Standard Speech
(ai.googleblog.com) -
Mapping roads through deep learning and weakly supervised training
(ai.facebook.com)#machine-learning #image-processing #GeoData #research #maps
-
A new model for word embeddings that are resilient to misspellings
(ai.facebook.com) -
Unifying visual embeddings for visual search at Pinterest
(medium.com)#machine-learning #image-processing #search #big-data #research
-
Video Understanding Using Temporal Cycle-Consistency Learning
(ai.googleblog.com) -
Article: Privacy Attacks on Machine Learning Models
(www.infoq.com)#data-science #machine-learning #security #research #privacy
-
EfficientNet-EdgeTPU: Creating Accelerator-Optimized Neural Networks with AutoML
(ai.googleblog.com) -
The Complete Guide to UX Research Methods
(www.toptal.com) -
Robust Neural Machine Translation
(ai.googleblog.com) -
Major trends in NLP: a review of 20 years of ACL research
(towardsdatascience.com) -
Learning Better Simulation Methods for Partial Differential Equations
(ai.googleblog.com) -
Introducing EvoGrad: A Lightweight Library for Gradient-Based Evolution
(eng.uber.com) -
Parrotron: New Research into Improving Verbal Communication for People with Speech Impairments
(ai.googleblog.com) -
Presentation: Learning from Machines
(www.infoq.com) -
ArchiGAN: a Generative Stack for Apartment Building Design
(devblogs.nvidia.com) -
Introducing the Plato Research Dialogue System: A Flexible Conversational AI Platform
(eng.uber.com) -
Multilingual Universal Sentence Encoder for Semantic Retrieval
(ai.googleblog.com) -
Recent Advances in Modern Computer Vision
(towardsdatascience.com) -
Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker
(ai.facebook.com) -
Advancing Semi-supervised Learning with Unsupervised Data Augmentation
(ai.googleblog.com) -
Predicting the Generalization Gap in Deep Neural Networks
(ai.googleblog.com) -
DLRM: An advanced, open source deep learning recommendation model
(ai.facebook.com) -
Predicting Bus Delays with Machine Learning
(ai.googleblog.com) -
Innovations in Graph Representation Learning
(ai.googleblog.com) -
The Quantum Menace
(blog.cloudflare.com) -
Off-Policy Classification - A New Reinforcement Learning Model Selection Method
(ai.googleblog.com)#data-science #AI #machine-learning #image-processing #research
-
A review of BERT based models
(towardsdatascience.com)#data-science #machine-learning #NLP #text-analysis #research
-
Presentation: wav2letter++: Facebook's Fast Open-source Speech Recognition System
(www.infoq.com)#deep-learning #data-science #NLP #audio-processing #research
-
Applying AutoML to Transformer Architectures
(ai.googleblog.com) -
Introducing Google Research Football: A Novel Reinforcement Learning Environment
(ai.googleblog.com) -
Advanced Topics in Deep Convolutional Neural Networks
(towardsdatascience.com) -
An Inside Look at Google Earth Timelapse
(ai.googleblog.com) -
Introducing TensorNetwork, an Open Source Library for Efficient Tensor Calculations
(ai.googleblog.com) -
EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling
(ai.googleblog.com) -
Presentation: The Future of Operating Systems on RISC-V
(www.infoq.com) -
Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
(ai.googleblog.com)#deep-learning #data-science #AI #image-processing #research
-
Presentation: Modern NLP for Pre-Modern Practitioners
(www.infoq.com) -
Meta-Learners - learning how to learn
(blog.fastforwardlabs.com) -
Graph Convolutional Networks for Geometric Deep Learning
(towardsdatascience.com)#deep-learning #data-science #algorithms #neural-net #research
-
Introducing Translatotron: An End-to-End Speech-to-Speech Translation Model
(ai.googleblog.com) -
The state of 3D object detection
(towardsdatascience.com)#machine-learning #image-processing #algorithms #neural-net #research
-
Using Deep Learning for finger-vein based biometric authentication
(towardsdatascience.com)#deep-learning #data-science #image-processing #research #biotech
-
Evaluating the Unsupervised Learning of Disentangled Representations
(ai.googleblog.com) -
SpecAugment: A New Data Augmentation Method for Automatic Speech Recognition
(ai.googleblog.com) -
What is Geometric Deep Learning?
(towardsdatascience.com) -
Improving scene understanding through panoptic segmentation
(code.fb.com) -
MorphNet: Towards Faster and Smaller Neural Networks
(ai.googleblog.com) -
Paper Summary. Stiffness: A New Perspective on Generalization in Neural Networks
(towardsdatascience.com) -
Review: Residual Attention Network — Attention-Aware Features (Image Classification)
(towardsdatascience.com) -
Understanding basics of measurements in Quantum Computation
(towardsdatascience.com) -
Using Reinforcement Learning to Design a Better Rocket Engine
(blog.insightdatascience.com) -
Open Questions about Generative Adversarial Networks
(distill.pub) -
Capturing Special Video Moments with Google Photos
(ai.googleblog.com) -
Illustrated: Efficient Neural Architecture Search
(towardsdatascience.com)#data-science #machine-learning #neural-net #visualisation #research
-
Unifying Physics and Deep Learning with TossingBot
(ai.googleblog.com) -
Visualizing memorization in RNNs
(distill.pub)#data-science #machine-learning #neural-net #visualisation #research
-
Simulated Policy Learning in Video Models
(ai.googleblog.com) -
Reducing the Need for Labeled Data in Generative Adversarial Networks
(ai.googleblog.com) -
Measuring the Limits of Data Parallel Training for Neural Networks
(ai.googleblog.com)#data-science #performance #neural-net #research #parallel-computing
-
Fast AI Assisted Annotation and Transfer Learning with Clara Train
(devblogs.nvidia.com) -
Harnessing Organizational Knowledge for Machine Learning
(ai.googleblog.com) -
Quantifying UX: How we validated the redesign of GitLab's settings pages
(about.gitlab.com) -
Connectivity Patterns in Deep Neural Networks
(towardsdatascience.com) -
An All-Neural On-Device Speech Recognizer
(ai.googleblog.com) -
RNN-Based Handwriting Recognition in Gboard
(ai.googleblog.com) -
Introducing GPipe, an Open Source Library for Efficiently Training Large-scale Neural Network Models
(ai.googleblog.com) -
Long-Range Robotic Navigation via Automated Reinforcement Learning
(ai.googleblog.com) -
Introducing Meta Reward Learning
(towardsdatascience.com) -
Learning to Generalize from Sparse and Underspecified Rewards
(ai.googleblog.com) -
On the Path to Cryogenic Control of Quantum Processors
(ai.googleblog.com) -
AI Safety Needs Social Scientists
(distill.pub) -
Introducing PlaNet: A Deep Planning Network for Reinforcement Learning
(ai.googleblog.com) -
Review: SegNet (Semantic Segmentation)
(towardsdatascience.com) -
Cross-lingual pretraining sets new state of the art for natural language understanding
(code.fb.com) -
Exploring the Relationship Between Quantum Computers and Machine Learning
(www.infoq.com) -
Teaching AI to learn speech the way children do
(code.fb.com) -
Transformer-XL: Unleashing the Potential of Attention Models
(ai.googleblog.com) -
How Uber Leverages Applied Behavioral Science at Scale
(eng.uber.com) -
Expanding the Application of Deep Learning to Electronic Health Records
(ai.googleblog.com) -
Soft Actor-Critic: Deep Reinforcement Learning for Robotics
(ai.googleblog.com) -
Trends in AI: NeurIPS 2018
(engineering.linkedin.com) -
Creating a Zoo of Atari-Playing Agents to Catalyze the Understanding of Deep Reinforcement Learning
(eng.uber.com) -
Strength in Numbers - an Overview of Data-Driven Design
(www.toptal.com) -
Bayesian Optimization & Quantum Computing
(towardsdatascience.com) -
POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer
(eng.uber.com) -
Beyond “How May I Help you? “
(medium.com) -
Deconstructing BERT: Distilling 6 Patterns from 100 Million Parameters
(towardsdatascience.com) -
Exploring Quantum Neural Networks
(ai.googleblog.com) -
On integrating symbolic inference into deep neural networks
(towardsdatascience.com) -
TF-Ranking: A Scalable TensorFlow Library for Learning-to-Rank
(ai.googleblog.com) -
Learning to Predict Depth on the Pixel 3 Phones
(ai.googleblog.com) -
Neural Egg Separation: Training ML systems to extract audio/video from noisy/cluttered environments
(code.fb.com) -
A Structured Approach to Unsupervised Depth Learning from Monocular Videos
(ai.googleblog.com) -
What Is Physically-Based Animation?
(towardsdatascience.com) -
Montezuma’s Revenge Solved by Go-Explore, a New Algorithm for Hard-Exploration Problems (Sets Records on Pitfall, Too)
(eng.uber.com) -
LPCNet: DSP-Boosted Neural Speech Synthesis
(hacks.mozilla.org) -
The Public Git Archive Story
(blog.sourced.tech) -
Toward a deeper understanding of the way AI agents see things
(code.fb.com) -
Accurate Online Speaker Diarization with Supervised Learning
(ai.googleblog.com) -
A Deeper Look into Embeddings — A Linguistic Approach
(towardsdatascience.com) -
Zero-shot learning: Using text to more accurately identify images
(code.fb.com) -
Using AI to help people with visual impairments share images on Facebook
(research.fb.com) -
Facebook Research at EMNLP
(research.fb.com) -
Google at EMNLP 2018
(ai.googleblog.com) -
Neural Networks For Music: A Journey Through Its History
(towardsdatascience.com) -
Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees
(ai.googleblog.com) -
Acoustic Detection of Humpback Whales Using a Convolutional Neural Network
(ai.googleblog.com) -
Facebook, NYU expand available languages for natural language understanding systems
(code.fb.com) -
Curiosity and Procrastination in Reinforcement Learning
(ai.googleblog.com) -
Significantly faster generation and training for AI-based audio systems
(code.fb.com) -
See Better and Further with Super Res Zoom on the Pixel 3
(ai.googleblog.com) -
Improving AI language understanding by combining multiple word representations
(code.fb.com) -
Applying Deep Learning to Metastatic Breast Cancer Detection
(ai.googleblog.com) -
Open Sourcing Active Question Reformulation with Reinforcement Learning
(ai.googleblog.com) -
Review: DeconvNet — Unpooling Layer (Semantic Segmentation)
(towardsdatascience.com) -
Mouse Cursor Control Using Facial Movements — An HCI Application
(towardsdatascience.com) -
Paper review: “Lessons from Building Static Analysis Tools at Google”.
(blog.sourced.tech) -
Rosetta: Understanding text in images and videos with machine learning
(code.fb.com) -
Consistent hashing with bounded loads, using a Red-Black Tree
(hackernoon.com) -
Synesthesia: The Sound of Style
(multithreaded.stitchfix.com) -
Introducing a New Framework for Flexible and Reproducible Reinforcement Learning Research
(ai.googleblog.com) -
DeepSig: Deep Learning for Wireless Communications
(devblogs.nvidia.com) -
Airbnb Engineering and Data Science at KDD 2018
(medium.com) -
Facebook Research at KDD 2018
(research.fb.com) -
Building Switch Software at Facebook Scale
(research.fb.com) -
Moving Beyond Translation with the Universal Transformer
(ai.googleblog.com) -
The Machine Learning Behind Android Smart Linkify
(ai.googleblog.com) -
MnasNet: Towards Automating the Design of Mobile Machine Learning Models
(ai.googleblog.com) -
New Dynamics for Topic Models
(blog.fastforwardlabs.com) -
Google Cirq and the New World of Quantum Programming
(hackernoon.com) -
Into a better Speech Synthesis Technology
(becominghuman.ai) -
Robust Factorization Machines
(medium.com) -
Article: Cats, Qubits, and Teleportation: The Spooky World of Quantum Computation Applications (Part 3)
(www.infoq.com) -
Automating Drug Discoveries Using Computer Vision
(ai.googleblog.com) -
Feature-wise transformations
(distill.pub) -
Getting Started with Quantum Programming
(hackernoon.com) -
Scalable Deep Reinforcement Learning for Robotic Manipulation
(ai.googleblog.com) -
Self-Supervised Tracking via Video Colorization
(ai.googleblog.com) -
Teaching Uncalibrated Robots to Visually Self-Adapt
(ai.googleblog.com) -
Translating music to predict a musician’s body movements
(research.fb.com) -
How Can Neural Network Similarity Help Us Understand Training and Generalization?
(ai.googleblog.com) -
Facebook open sources DensePose
(research.fb.com) -
DeepMind’s Amazing Mix & Match RL Technique
(hackernoon.com) -
Kicking the tires of quantum processors
(hackernoon.com) -
Overscripted! Digging into JavaScript execution at scale
(hacks.mozilla.org) -
Using NLP to Detect Linguistic Cues in Alzheimer's Disease Patients
(towardsdatascience.com) -
Advances in Semantic Textual Similarity
(ai.googleblog.com) -
Balanced Partitioning and Hierarchical Clustering at Scale
(ai.googleblog.com) -
Deep Learning for Electronic Health Records
(ai.googleblog.com) -
Google Duplex: An AI System for Accomplishing Real-World Tasks Over the Phone
(ai.googleblog.com) -
Looking to Listen: Audio-Visual Speech Separation
(ai.googleblog.com) -
The Question of Quantum Supremacy
(ai.googleblog.com) -
The Question of Quantum Supremacy
(research.googleblog.com) -
Embodied Question Answering: A goal-driven approach to autonomous agents
(code.facebook.com) -
Advancing state-of-the-art image recognition with deep learning on hashtags
(code.facebook.com) -
Deep Learning and a New Programming Paradigm
(towardsdatascience.com) -
Designing a face recognition application for people with visual impairments
(research.fb.com) -
DeepVariant Accuracy Improvements for Genetic Datatypes
(research.googleblog.com) -
Using Machine Learning to Discover Neural Network Optimizers
(research.googleblog.com) -
Expressive Speech Synthesis with Tacotron
(research.googleblog.com) -
Paper Repro: Deep Neuroevolution
(towardsdatascience.com) -
Reformulating Chemistry for More Efficient Quantum Computation
(research.googleblog.com) -
Using Deep Learning to Facilitate Scientific Image Analysis
(research.googleblog.com) -
Using Evolutionary AutoML to Discover Neural Network Architectures
(research.googleblog.com) -
Semantic Image Segmentation with DeepLab in Tensorflow
(research.googleblog.com) -
Open Sourcing the Hunt for Exoplanets
(research.googleblog.com) -
A Preview of Bristlecone, Google’s New Quantum Processor
(research.googleblog.com) -
Deep Neural Networks for Survival Analysis Based on a Multi-Task Framework
(medium.com) -
Neural Voice Cloning with a Few Samples
(research.baidu.com)#deep-learning #machine-learning #audio-processing #research
-
Using Deep Learning for Structured Data with Entity Embeddings
(towardsdatascience.com) -
Assessing Cardiovascular Risk Factors with Computer Vision
(research.googleblog.com) -
A HCI Researcher’s Summary on AAAI 2018 Conference!
(towardsdatascience.com) -
Announcing Tensor Comprehensions
(research.fb.com) -
The Instant Motion Tracking Behind Motion Stills AR
(research.googleblog.com) -
Introducing the Hardware Robot Information Model (HRIM)
(hackernoon.com) -
Under the hood: Multilingual embeddings
(code.facebook.com) -
Facebook open sources Detectron
(research.fb.com) -
How machine learning can be used to write more secure computer programs
(www.oreilly.com)#machine-learning #programming-languages #security #research #podcast
-
What if I told you database indexes could be learned?
(towardsdatascience.com) -
Tacotron 2: Generating Human-like Speech from Text
(research.googleblog.com) -
Welcoming the Era of Deep Neuroevolution
(eng.uber.com) -
Introducing NIMA: Neural Image Assessment
(research.googleblog.com) -
Improving End-to-End Models For Speech Recognition
(research.googleblog.com) -
Securing communications between Google services with Application Layer Transport Security
(security.googleblog.com) -
TFGAN: A Lightweight Library for Generative Adversarial Networks
(research.googleblog.com) -
PaddlePaddle Fluid: Elastic Deep Learning on Kubernetes
(research.baidu.com) -
Deep Learning Scaling is Predictable, Empirically
(research.baidu.com) -
DeepVariant: Highly Accurate Genomes With Deep Neural Networks
(research.googleblog.com) -
Facebook showcases latest research at NIPS 2017
(research.fb.com) -
Google at NIPS 2017
(research.googleblog.com) -
Bringing still photos to life and 3D photography to your phone
(research.fb.com) -
Understanding Medical Conversations
(research.googleblog.com) -
Malware Detection in Executables Using Neural Networks
(devblogs.nvidia.com) -
SLING: A Natural Language Frame Semantic Parser
(research.googleblog.com) -
Fused Video Stabilization on the Pixel 2 and Pixel 2 XL
(research.googleblog.com) -
State of Deep Learning in Computer Vision
(tech.showmax.com) -
AutoML for large scale image classification and object detection
(research.googleblog.com) -
Closing the Simulation-to-Reality Gap for Deep Robotic Learning
(research.googleblog.com) -
Deep Speech 3:Exploring Neural Transducers for End-to-End Speech Recognition
(research.baidu.com)#AI #machine-learning #neural-net #audio-processing #research
-
Visual reasoning and dialog: Towards natural language conversations about visual data
(research.fb.com) -
Facebook SOSP papers present real-world solutions to complex system challenges
(research.fb.com) -
Deep Voice 3: 2000-Speaker Neural Text-to-Speech
(research.baidu.com) -
Mixed Precision Training
(research.baidu.com) -
A State-of-the-Art Method for Generating Photo-Realistic Textures in Real Time
(jobs.zalando.com)#deep-learning #machine-learning #image-processing #research
-
Globally Normalized Reader
(research.baidu.com) -
Facebook memories: the research behind the products that connect you with your past
(research.fb.com) -
Introducing Social Hash Partitioner, a scalable distributed hypergraph partitioner
(research.fb.com) -
Sharing new machine learning insights at ICML 2017
(research.fb.com) -
Google at ICML 2017
(research.googleblog.com)