Related papers: Transfer learning via interpolating structures
Data for training structural health monitoring (SHM) systems are often expensive and/or impractical to obtain, particularly for labelled data. Population-based SHM (PBSHM) aims to address this limitation by leveraging data from multiple…
This study proposes a learning-based method with domain adaptability for input estimation of vehicle suspension systems. In a crowdsensing setting for bridge health monitoring, vehicles carry sensors to collect samples of the bridge's…
Humans leverage multiple sensor modalities when interacting with objects and discovering their intrinsic properties. Using the visual modality alone is insufficient for deriving intuition behind object properties (e.g., which of two boxes…
A transfer learning paradigm is proposed for "knowledge" transfer between the human brain and convolutional neural network (CNN) for a construction hazard categorization task. Participants' brain activities are recorded using…
People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in…
Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
Determining the different conformational states of a protein and the transition paths between them is key to fully understanding the relationship between biomolecular structure and function. This can be accomplished by sampling protein…
In the robotics literature, experience transfer has been proposed in different learning-based control frameworks to minimize the costs and risks associated with training robots. While various works have shown the feasibility of transferring…
In contemporary educational systems, academic performance indicators play a central role in institutional evaluation and in the interpretation of student trajectories. However, under conditions of rapid technological change, the inferential…
Crosslingual transfer is crucial to contemporary language models' multilingual capabilities, but how it occurs is not well understood. We ask what happens to a monolingual language model when it begins to be trained on a second language.…
Humans can learn from very few samples, demonstrating an outstanding generalization ability that learning algorithms are still far from reaching. Currently, the most successful models demand enormous amounts of well-labeled data, which are…
Medical internet of things leads to revolutionary improvements in medical services, also known as smart healthcare. With the big healthcare data, data mining and machine learning can assist wellness management and intelligent diagnosis, and…
Many modern learning tasks require models that can take inputs of varying sizes. Consequently, dimension-independent architectures have been proposed for domains where the inputs are graphs, sets, and point clouds. Recent work on graph…
A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by…
Our current world is linked by a complex mesh of networks where information, people and goods flow. These networks are interdependent each other, and present structural and dynamical features different from those observed in isolated…
Imitation is a basic updating mechanism for strategy evolution in structured populations, determining how individuals sample social information and translate it into behavioral changes. Higher-order networks, such as hypergraphs, generalize…
Heterogeneity is one important feature of complex systems, leading to the complexity of their construction and analysis. Moving the heterogeneity at model level helps in mastering the difficulty of composing heterogeneous models which…
Transfer learning where the behavior of extracting transferable knowledge from the source domain(s) and reusing this knowledge to target domain has become a research area of great interest in the field of artificial intelligence.…
This work presents a naive algorithm for parameter transfer between different architectures with a computationally cheap injection technique (which does not require data). The primary objective is to speed up the training of neural networks…