中文
相关论文

相关论文: Navigating the Latent Space Dynamics of Neural Mod…

200 篇论文

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

机器学习 · 计算机科学 2020-10-13 Denis Kuzminykh , Laida Kushnareva , Timofey Grigoryev , Alexander Zatolokin

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

计算与语言 · 计算机科学 2018-12-12 Artidoro Pagnoni , Kevin Liu , Shangyan Li

This study presents a novel representation learning model tailored for dynamic networks, which describes the continuously evolving relationships among individuals within a population. The problem is encapsulated in the dimension reduction…

机器学习 · 统计学 2024-12-17 Haixu Wang , Jiguo Cao , Jian Pei

We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations. The power of the model lies in its ability…

信息检索 · 计算机科学 2016-08-26 Christophe Van Gysel , Maarten de Rijke , Evangelos Kanoulas

To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential. We propose to introduce a novel cross-domain latent modulation mechanism to a variational autoencoder framework so as to…

机器学习 · 计算机科学 2024-02-01 Jinyong Hou , Jeremiah D. Deng , Stephen Cranefield , Xuejie Din

In this paper, we present a novel learning approach based on Neurovectors, an innovative paradigm that structures information through interconnected nodes and vector relationships for tabular data processing. Unlike traditional artificial…

机器学习 · 计算机科学 2025-06-10 J. C. Husillos , A. Gallego , A. Roma , A. Troncoso

Despite decades of research, understanding human manipulation activities is, and has always been, one of the most attractive and challenging research topics in computer vision and robotics. Recognition and prediction of observed human…

计算机视觉与模式识别 · 计算机科学 2021-10-27 Gamze Akyol , Sanem Sariel , Eren Erdal Aksoy

This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our…

计算机视觉与模式识别 · 计算机科学 2018-01-30 Guillaume Lample , Neil Zeghidour , Nicolas Usunier , Antoine Bordes , Ludovic Denoyer , Marc'Aurelio Ranzato

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either…

计算机视觉与模式识别 · 计算机科学 2022-06-22 Patrick M. Jensen , Udaranga Wickramasinghe , Anders B. Dahl , Pascal Fua , Vedrana A. Dahl

In this paper, we propose DeepTree, a novel method for modeling trees based on learning developmental rules for branching structures instead of manually defining them. We call our deep neural model situated latent because its behavior is…

机器学习 · 计算机科学 2023-05-10 Xiaochen Zhou , Bosheng Li , Bedrich Benes , Songlin Fei , Sören Pirk

Attractor neural networks consider that neural information is stored as stationary states of a dynamical system formed by a large number of interconnected neurons. The attractor property empowers a neural system to encode information…

神经元与认知 · 定量生物学 2024-10-10 Yujun Li , Tianhao Chu , Si Wu

Modern generative models demonstrate impressive capabilities, likely stemming from an ability to identify and manipulate abstract concepts underlying their training data. However, fundamental questions remain: what determines the concepts a…

机器学习 · 计算机科学 2024-12-12 Core Francisco Park , Maya Okawa , Andrew Lee , Hidenori Tanaka , Ekdeep Singh Lubana

Manifold-valued data naturally arises in medical imaging. In cognitive neuroscience, for instance, brain connectomes base the analysis of coactivation patterns between different brain regions on the analysis of the correlations of their…

机器学习 · 统计学 2019-11-20 Nina Miolane , Susan Holmes

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Matthew Gwilliam , Xiao Wang , Xuefeng Hu , Zhenheng Yang

When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object…

计算机视觉与模式识别 · 计算机科学 2016-08-17 Andrew Brock , Theodore Lim , J. M. Ritchie , Nick Weston

In this lecture I will present some models of neural networks that have been developed in the recent years. The aim is to construct neural networks which work as associative memories. Different attractors of the network will be identified…

凝聚态物理 · 物理学 2008-02-03 Giorgio Parisi

Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…

计算机视觉与模式识别 · 计算机科学 2023-02-28 Benjamin L. Badger

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Slow adaption processes, like synaptic and intrinsic plasticity, abound in the brain and shape the landscape for the neural dynamics occurring on substantially faster timescales. At any given time the network is characterized by a set of…

神经元与认知 · 定量生物学 2015-02-13 Claudius Gros , Mathias Linkerhand , Valentin Walther

Neural networks can accurately forecast complex dynamical systems, yet how they internally represent underlying latent geometry remains poorly understood. We study neural forecasters through the lens of representational alignment,…