Efficient Memory-Enhanced Transformer for Long-Document Summarization in Low-Resource Regimes
Sensors, 2023 Long document summarization poses obstacles to current generative transformer-based models because of the broad context to process and understand. Indeed, detecting long-range dependencies is still challenging for today’s state-of-the-art solutions ...
Gianluca Moro +5 more
doaj +1 more source
Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting [PDF]
, 2020 Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting.
Lee, Ickjai, Liu, Hong-Bin
core +2 more sources
Conducting Causal Analysis by Means of Approximating Probabilistic Truths
Entropy, 2022 The current paper develops a probabilistic theory of causation using measure-theoretical concepts and suggests practical routines for conducting causal inference. The theory is applicable to both linear and high-dimensional nonlinear models.
Bo Pieter Johannes Andrée
doaj +1 more source
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference [PDF]
, 2017 We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network.
Han, Xiaoguang +4 more
core +2 more sources
Hypothesis Only Baselines in Natural Language Inference [PDF]
, 2018 We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI). Especially when an NLI dataset assumes inference is occurring based purely on the relationship between a context and a hypothesis, it follows that assessing entailment
Haldar, Aparajita +4 more
core +3 more sources
Bayesian Learning and Predictability in a Stochastic Nonlinear Dynamical Model [PDF]
, 2012 Bayesian inference methods are applied within a Bayesian hierarchical modelling framework to the problems of joint state and parameter estimation, and of state forecasting.
Campbell, Edward P. +4 more
core +3 more sources
Fast neural network inference on FPGAs for triggering on long-lived particles at colliders
Machine Learning: Science and Technology, 2023 Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation.
Andrea Coccaro +4 more
doaj +1 more source
The Analysis of Non-Stationary Pooled Time-Series Cross-Section-Data [PDF]
International Journal of Conflict and Violence, 2015 It is common in macro-level research on violent crime to analyze datasets combining a cross-section (N units) with a time-series (T periods) dimension. A large body of methodological literature accumulated since the 1990s raises questions regarding the ...
Christoph Birkel
doaj +2 more sources
Scene Graph Generation Model Combined with External Knowledge Base and Adaptive Reasoning [PDF]
Jisuanji gongcheng, 2022 To obtain better contextual information in the Scene Graph Generation(SGG) network while reducing the impact of dataset bias, this study proposes a SGG model based on an external knowledge base and adaptive reasoning.First, the proposed model uses a ...
WANG Yini, GAO Yongbin, WAN Weibing, YANG Shuqun, GUO Ruyan
doaj +1 more source
Cooperation and Social Rules Emerging From the Principle of Surprise Minimization
Frontiers in Psychology, 2021 The surprise minimization principle has been applied to explain various cognitive processes in humans. Originally describing perceptual and active inference, the framework has been applied to different types of decision making including long-term ...
Mattis Hartwig, Achim Peters
doaj +1 more source