InfoQ Homepage Deep Learning Content on InfoQ
-
Google Introduces TensorFlow Enterprise in Beta
In a recent blog post, Google announced TensorFlow Enterprise, a cloud-based TensorFlow machine learning service that includes enterprise-grade support and managed services.
-
PyTorch and TensorFlow: Which ML Framework is More Popular in Academia and Industry
An article that was recently published on the gradient is examining the current state of Machine Learning frameworks in 2019. The article is utilizing some metrics to argue the point that PyTorch is quickly becoming the dominant framework for research, whereas TensorFlow is the dominant framework for applications in the industry. In this article we will dive into their differences.
-
Microsoft and University of Maryland Researchers Announce FreeLB Adversarial Training System
Researchers from Microsoft and the University of Maryland (UMD) announced Free Large-Batch (FreeLB), a new adversarial training technique for deep-learning natural-language processing (NLP) systems that improves accuracy, increasing RoBERTa's scores on the General Language Understanding Evaluation (GLUE) benchmark and achieving the highest score on AI2 Reasoning Challenge (ARC) benchmark.
-
Facebook Open-Sources CraftAssist Framework for AI Assistants in Minecraft
Facebook AI researchers open-sourced CraftAssist, a framework for building interactive assistants for the Minecraft video game. The bots use natural language understanding (NLU) to parse and execute text commands from human players, such as requests to build houses in the game world. The framework's modular structure can be extended by researchers to perform their own ML experiments.
-
Facebook Releases AI Code Search Datasets
Facebook AI released a dataset containing coding questions paired with code-snippet answers, intended for evaluating AI-based natural-language code search systems. The release also includes benchmark results for several of Facebook's own code-search models and a training corpus of over 4 million Java methods parsed from over 24,000 GitHub repositories.
-
Databricks' Unified Analytics Platform Supports AutoML Toolkit
Databricks recently announced the Unified Data Analytics Platform, including an automated machine learning tool called AutoML Toolkit. The toolkit can be used to automate various steps of the data science workflow.
-
AI Researchers' Open-Source Model Explanation Toolkit AllenNLP Interpret
Researchers from the Allen Institute for AI and University of California, Irvine, have released AllenNLP Interpret, a toolkit for explaining the results from NLP models. The extensible toolkit includes several built-in methods for interpretation and visualization components, as well as examples using AllenNLP to explain the results of state-of-the art NLP models including BERT and RoBERTa.
-
Google Releases Two New NLP Dialog Datasets
Researchers from Google AI released two new dialog datasets for natural-language processing (NLP) development: Coached Conversational Preference Elicitation (CCPE) and Taskmaster-1. The datasets contain thousands of conversations as well as labels and annotations for training digital assistants to better determine users' preferences and intentions.
-
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.
-
Waymo Shares Autonomous Vehicle Dataset for Machine Learning
Waymo, the self-driving technology company, released a dataset containing sensor data collected by their autonomous vehicles during more than five hours of driving. The set contains high-resolution data from lidar and camera sensors collected in several urban and suburban environments in a wide variety of driving conditions and includes labels for vehicles, pedestrians, cyclists, and signage.
-
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%.