Related papers: Transfer Learning for Transient Classification: Fr…

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and…

Model-based RL is a promising approach for real-world robotics due to its improved sample efficiency and generalization capabilities compared to model-free RL. However, effective model-based RL solutions for vision-based real-world…

Quantum Transfer Learning (QTL) offers a promising approach for visual quantum machine learning under near-term constraints, where limited qubit counts, shallow circuit depths, and costly hybrid optimization restrict end-to-end quantum…

Federated learning involves training statistical models over edge devices such as mobile phones such that the training data is kept local. Federated Learning (FL) can serve as an ideal candidate for training spatial temporal models that…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

The Vera C. Rubin Observatory will increase the number of observed supernovae (SNe) by an order of magnitude; however, it is impossible to spectroscopically confirm the class for all the SNe discovered. Thus, photometric classification is…

Modern software systems provide many configuration options which significantly influence their non-functional properties. To understand and predict the effect of configuration options, several sampling and learning strategies have been…

Zero-shot learning (ZSL) recognizes the unseen classes by conducting visual-semantic interactions to transfer semantic knowledge from seen classes to unseen ones, supported by semantic information (e.g., attributes). However, existing ZSL…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

Learning from demonstrations (LfD) is an efficient paradigm to train AI agents. But major issues arise when there are differences between (a) the demonstrator's own sensory input, (b) our sensors that observe the demonstrator and (c) the…

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…

We propose a learning problem involving adapting a pre-trained source model to the target domain for classifying all classes that appeared in the source data, using target data that covers only a partial label space. This problem is…

The Zwicky Transient Facility (ZTF) is a next-generation optical synoptic survey that builds on the experience and infrastructure of the Palomar Transient Factory (PTF). Using a new 47 deg$^2$ survey camera, ZTF will survey more than an…

Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a…

Efficient prediction of internet traffic is an essential part of Self Organizing Network (SON) for ensuring proactive management. There are many existing solutions for internet traffic prediction with higher accuracy using deep learning.…

Machine learning using quantum convolutional neural networks (QCNNs) has demonstrated success in both quantum and classical data classification. In previous studies, QCNNs attained a higher classification accuracy than their classical…

Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source…

Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share…

Only learning one projection matrix from original samples to the corresponding binary labels is too strict and will consequentlly lose some intrinsic geometric structures of data. In this paper, we propose a novel transition subspace…

Effective internet traffic prediction in smaller ISP networks is challenged by limited data availability. This paper explores this issue using transfer learning and data augmentation techniques with two LSTM-based models, LSTMSeq2Seq and…