Tag: Deep Neural Networks

AI Machine Learning & Data Science Research

Gem-Miner: Finding Lottery Tickets at Initialization and Bettering All Baselines at 19x Faster Speeds

In the new paper Rare Gems: Finding Lottery Tickets at Initialization, a research team from Carnegie Mellon University, MBZUAI, Petuum, Inc and the University of Wisconsin-Madison proposes GEM-MINER, an algorithm that finds sparse subnetworks at initialization trainable to accuracy that is comparable or better than iterative magnitude pruning (IMP) with warm-up.

AI Machine Learning & Data Science Research

NVIDIA & UW Introduce Factory: A Set of Physics Simulation Methods and Learning Tools for Contact-Rich Robotic Assembly

In the new paper Factory: Fast Contact for Robotic Assembly, a research team from NVIDIA and the University of Washington introduces Factory, a set of physics simulation methods and robot learning tools for simulating contact-rich interactions in assembly with high accuracy, efficiency, and robustness.

AI Computer Vision & Graphics Machine Learning & Data Science Research

Google Brain’s UViM: A Unified Approach for Modelling Diverse Vision Tasks Without Modifications

In the new paper UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes, a Google Brain research team proposes UViM, a unified approach that leverages language modelling and discrete representation learning to enable the modelling of a wide range of computer vision tasks without task-specific modifications.

AI Machine Learning & Data Science Nature Language Tech Research

Google’s Imagen Text-to-Image Diffusion Model With Deep Language Understanding Defeats DALL-E 2

In the new paper Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding, a Google Brain research team presents Imagen, a text-to-image diffusion model that combines deep language understanding and photorealistic image generation capabilities to achieve a new state-of-the-art FID score of 7.27 on the COCO dataset.

AI Machine Learning & Data Science Nature Language Tech Research

Fact Tracing in LMs: MIT & Google Dataset and Benchmark Track Learned Knowledge Back to the Training Data

In the new paper Tracing Knowledge in Language Models Back to the Training Data, a team from MIT CSAIL and Google Research proposes a benchmark for tracing language models’ assertions to the associated training data, aiming to establish a principled ground truth and mitigate high compute demands for large neural language model training.

AI Machine Learning & Data Science Nature Language Tech Research

Tokyo U & Google Brain Train Large Language Models as Zero-Shot Reasoners

In the new paper Large Language Models are Zero-Shot Reasoners, a research team from the University of Tokyo and Google Brain demonstrates that large language models (LLMs) can become good zero-shot reasoners through the addition of a simple prompt — “Let’s think step by step” — that elicits a step-by-step thinking process before each question is answered. Their Zero-shot-CoT model achieves huge performance gains compared to the zero-shot baseline.

AI Machine Learning & Data Science Research

Meta AI Extends MAEs to Video for Self-Supervised Representation Learning With Minimal Domain Knowledge

In the new paper Masked Autoencoders As Spatiotemporal Learners, a Meta AI research team extends masked autoencoders (MAE) to spatiotemporal representation learning for video. The novel approach introduces negligible inductive biases on space-time while achieving strong empirical results compared to vision transformers (ViTs) and outperforms supervised pretraining by large margins.

AI Machine Learning & Data Science Research

DeepMind’s Meta-Learning Sparse Compression Networks Set New SOTA on Diverse Modality Data Compression

In the new paper Meta-Learning Sparse Compression Networks, a DeepMind research team proposes steps for scaling implicit neural representations (INRs). The resulting meta-learning sparse compression networks can represent diverse data modalities such as images, manifolds, signed distance functions, 3D shapes, and scenes, achieving state-of-the-art results on some of them.

AI Machine Learning & Data Science Research

Huawei Rethinks Logical Synthesis, Proposing a Practical RL-based Approach That Achieves High Efficiency

In the new paper Rethinking Reinforcement Learning Based Logic Synthesis, a research team from Huawei Noah’s Ark Lab develops a novel reinforcement learning-based logic synthesis method to automatically recognize critical operators and produce common operator sequences that are generalizable to unseen circuits.

AI Machine Learning & Data Science Research

AI21 Labs’ Augmented Frozen Language Models Challenge Conventional Fine-Tuning Approaches Without Sacrificing Versatility

In the new paper Standing on the Shoulders of Giant Frozen Language Models, AI21 Labs researchers propose three novel methods for learning small neural modules that specialize a frozen language model to different tasks. Their compute-saving approach outperforms conventional frozen model methods and challenges fine-tuning performance without sacrificing model versatility.

AI Computer Vision & Graphics Machine Learning & Data Science Research

Microsoft Azure Introduces i-Code: A General Framework That Enables Flexible Multimodal Representation Learning

In the new paper i-Code: An Integrative and Composable Multimodal Learning Framework, a Microsoft Azure Cognitive Services Research team presents i-Code, a self-supervised pretraining framework that enables the flexible integration of vision, speech, and language modalities and learns their vector representations in a unified manner.

AI Computer Vision & Graphics Machine Learning & Data Science Research

LSTM Is Back! A Deep Implementation of the Decades-old Architecture Challenges ViTs on Long Sequence Modelling

A research team from Rikkyo University and AnyTech Co., Ltd. examines the suitability of different inductive biases for computer vision and proposes Sequencer, an architectural alternative to ViTs that leverages long short-term memory (LSTM) rather than self-attention layers to achieve ViT-competitive performance on long sequence modelling.

AI Machine Learning & Data Science Research

Tsinghua U & BAAI’s CogView2 Achieves SOTA Competitive Text-to-Image Generation With 10x Speedups

In the new paper CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers, Tsinghua University and the Beijing Academy of Artificial Intelligence researchers pretrain a Cross-Modal general Language Model (CogLM) for text and image token prediction and finetune it for fast super-resolution. The resulting CogView2 hierarchical text-to-image system achieves significant speedups while generating images with better quality at comparable resolutions.

AI Computer Vision & Graphics Machine Learning & Data Science Research

UC Berkeley & Intel’s Photorealistic Denoising Method Boosts Video Quality on Moonless Nights

In the new paper Dancing Under the Stars: Video Denoising in Starlight, a research team from UC Berkeley and Intel Labs leverages a GAN-tuned, physics-based noise model to represent camera noise under low light conditions and trains a novel denoiser that, for the first time, achieves photorealistic video denoising in starlight.

AI Machine Learning & Data Science Research

Alibaba’s USI: A Unified Scheme for Training Any Backbone on ImageNet That Delivers Top Results Without Hyperparameter Tuning

In the new paper Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results, a research team from Alibaba Group’s DAMO Academy introduces USI (Unified Scheme for ImageNet), a unified scheme for training any backbone on ImageNet that does not require adjustments or hyperparameter tuning between different models, and consistently yields top model results in terms of accuracy and efficiency.

AI Machine Learning & Data Science Research

Ithaca Paper Published in Nature: The First DNN Designed for Textual Restoration and Geographical and Chronological Attribution of Ancient Greek Inscriptions

A research team from DeepMind, Ca’ Foscari University of Venice, University of Oxford and Athens University of Economics and Business introduces Ithaca, a deep neural network (DNN) designed for textual restoration and geographical and chronological attribution of ancient Greek inscriptions.

AI Machine Learning & Data Science Research

Microsoft & OpenAI’s µTransfer Zero-Shot Hyperparameter Transfer Method Tunes GPT-3’s Hyperparameters on a Single GPU

In the new paper Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer, Microsoft and OpenAI researchers propose µTransfer, a method that leverages Maximal Update Parametrization (µP) to zero-shot transfer hyperparameters from small models and obtain near-optimal parameters on large models without directly tuning them.

AI Machine Learning & Data Science Research

Microsoft & OneFlow Leverage the Efficient Coding Principle to Design Unsupervised DNN Structure-Learning That Outperforms Human-Designed Structures

A research team from OneFlow and Microsoft takes a step toward automatic deep neural network structure design, exploring unsupervised structure-learning and leveraging the efficient coding principle, information theory and computational neuroscience to design structure learning without label information.