AI Technology & Industry Review
In the new paper Promptagator: Few-shot Dense Retrieval From 8 Examples, a Google Research team proposes Prompt-based Query Generation for Retriever (Promptagator), a novel and simple approach for few-shot retrieval that leverages large language model (LLM) prompting to generate synthetic task-specific training data.
In the new paper MO2: Model-Based Offline Options, a DeepMind research team introduces Model-Based Offline Options (MO2), an offline hindsight bottleneck options framework that supports sample-efficient option discovery over continuous state-action spaces for efficient skill transfer to new tasks.
In the new paper Neural Collapse: A Review on Modelling Principles and Generalization, researchers from New York University analyze Neural Collapse (NC) and present a thought model to explain the effects of variance collapse, aiming at a better understanding of the generalization capabilities of neural networks.
A research team from Facebook shows how the power of transfer learning can enable pretraining on non-IDE, non-autocompletion and different-language example code sequences before fine-tuning on the autocompletion prediction task to improve model accuracy by over 50 percent on very small fine-tuning datasets and over 10 percent on 50k labelled examples.
A research team from Hugging Face shows that prompting is indeed beneficial for fine-tuning pretrained language models, and that this benefit can be quantified as worth hundreds of data points on average across classification tasks.
Researchers from the University of Sheffield, Beihang University, and Open University’s Knowledge Media Institute have proposed a transfer learning approach that can automatically process historical texts at a semantic level to generate modern language summaries.
Despite being less accurate on ImageNet, adversarially robust neural networks can match or improve their standard counterparts’ transfer performance.
Synced invited Samuel R. Bowman, an Assistant Professor at New York University who works on artificial neural network models for natural language understanding, to share his thoughts on the “Text-to-Text Transfer Transformer” (T5) framework.
At last week’s Re•Work AI in Finance Conference in New York, researchers and engineers from banks and academia alike shared their thoughts on current AI research and applications in the finance world.
To make ML-based solutions available for a wider variety of deployment scenarios, Waymo’s autonomous driving team has collaborated with Google AI Brain Team researchers on a system that automates the creation of high quality and low latency neural networks on existing AutoML architectures.
The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) opened today in Salt Lake City, USA. The CVPR organizing committee used the occasion to announce its coveted Best Paper and Best Student Paper selections.
This paper systematically studies how a convolutional neural network, trained on ImageNet for image classification tasks, works on medical images – or more precisely on ultrasound images – for the “Kidney Detection” problem.