InfoQ Homepage Deep Learning Content on InfoQ
-
Facebook Open-Sources RoBERTa: an Improved Natural Language Processing Model
Facebook AI open-sourced a new deep-learning natural-language processing (NLP) model, Robustly-optimized BERT approach (RoBERTa). Based on Google's BERT pre-training model, RoBERTa includes additional pre-training improvements that achieve state-of-the-art results on several benchmarks, using only unlabeled text from the world-wide web, with minimal fine-tuning and no data augmentation.
-
Facebook, Microsoft, and Partners Announce Deepfake Detection Challenge
Facebook, Microsoft, the Partnership on AI, and researchers from several universities have created the Deepfake Detection Challenge (DDC), a contest to produce AI that can detect misleading images and video that have been created by AI. The challenge includes several grants and awards for the teams that create the best AI solution, using the DDC's dataset of real and fake videos.
-
Denis Magda on Continuous Deep Learning with Apache Ignite
At the recent ApacheCon North America, Denis Magda spoke on continuous machine learning with Apache Ignite, an in-memory data grid. Ignite simplifies the machine-learning pipeline by performing training and hosting models in the same cluster that stores the data, and can perform "online" training to incrementally improve models when new data is available.
-
New Technique Speeds up Deep-Learning Inference on TensorFlow by 2x
Researchers at North Carolina State University recently presented a paper at the International Conference on Supercomputing (ICS) on their new technique, "deep reuse" (DR), that can speed up inference time for deep-learning neural networks running on TensorFlow by up to 2x, with almost no loss of accuracy.
-
Predicting the Future, Amazon Forecast Reaches General Availability
In a recent blog post, Amazon announced the general availability (GA) of Amazon Forecast, a fully managed, time series data forecasting service. Amazon Forecast uses deep learning from multiple datasets and algorithms to make predictions in the areas of product demand, travel demand, financial planning, SAP and Oracle supply chain planning and cloud computing usage.
-
University Research Teams Open-Source Natural Adversarial Image DataSet for Computer-Vision AI
Research teams from three universities recently released a dataset called ImageNet-A, containing natural adversarial images: real-world images that are misclassified by image-recognition AI. When used as a test-set on several state-of-the-art pre-trained models, the models achieve an accuracy rate of less than 3%.
-
Microsoft Open-Sources TensorWatch AI Debugging Tool
Microsoft Research open-sourced TensorWatch, their debugging tool for AI and deep-learning. TensorWatch supports PyTorch as well as TensorFlow eager tensors, and allows developers to interactively debug training jobs in real-time via Jupyter notebooks, or to build their own custom UIs in Python.
-
Researchers Develop Technique for Reducing Deep-Learning Model Sizes for Internet of Things
Researchers from Arm Limited and Princeton University have developed a technique that produces deep-learning computer-vision models for internet-of-things (IoT) hardware systems with as little as 2KB of RAM. By using Bayesian optimization and network pruning, the team is able to reduce the size of image recognition models while still achieving state-of-the-art accuracy.
-
Google Releases Post-Training Integer Quantization for TensorFlow Lite
Google announced new tooling for their TensorFlow Lite deep-learning framework that reduces the size of models and latency of inference. The tool converts a trained model's weights from floating-point representation to 8-bit signed integers. This reduces the memory requirements of the model and allows it to run on hardware without floating-point accelerators and without sacrificing model quality.
-
Google Releases TensorFlow.Text Library for Natural Language Processing
Google released a TensorFlow.Text, a new text-processing library for their TensorFlow deep-learning platform. The library allows several common text pre-processing activities, such as tokenization, to be handled by the TensorFlow graph computation system, improving consistency and portability of deep-learning models for natural-language processing.
-
Google Releases Deep Learning Containers into Beta
In a recent blog post, Google announced Deep Learning Containers, allowing customers to get Machine Learning projects up and running quicker. Deep Learning consists of numerous performance-optimized Docker containers that come with a variety of tools necessary for deep learning tasks already installed.
-
Facebook Open-Sources Deep-Learning Recommendation Model DLRM
Facebook AI Research announced the open-source release of a deep-learning recommendation model, DLRM, that achieves state-of-the-art accuracy in generating personalized recommendations. The code is available on GitHub, and includes versions for the PyTorch and Caffe2 frameworks.
-
AWS Enhances Deep Learning AMI, AI Services SageMaker Ground Truth, and Rekognition
Amazon Web Services (AWS) announced updates to their Deep Learning virtual machine image, as well as improvements to their AI services SageMaker Ground Truth and Rekognition.
-
MIT Researchers Open-Source AutoML Visualization Tool ATMSeer
A research team from MIT, Hong Kong University, and Zhejiang University has open-sourced ATMSeer, a tool for visualizing and controlling automated machine-learning processes.
-
Google Uses Mannequin Challenge Videos to Learn Depth Perception
Google AI Research published a paper describing their work on depth perception from two-dimensional images. Using a training dataset created from YouTube videos of the Mannequin Challenge, researchers trained a neural network that can reconstruct depth information from videos of moving people, taken by moving cameras.