Related papers: Efficient Bayesian Updates for Deep Active Learnin…
Active deep learning classification of hyperspectral images is considered in this paper. Deep learning has achieved success in many applications, but good-quality labeled samples are needed to construct a deep learning network. It is…
Active learning (AL) is a principled strategy to reduce annotation cost in data-hungry deep learning. However, existing AL algorithms focus almost exclusively on unimodal data, overlooking the substantial annotation burden in multimodal…
Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL)…
We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian…
Deep reinforcement learning (RL) has achieved remarkable success in solving complex tasks through its integration with deep neural networks (DNNs) as function approximators. However, the reliance on DNNs has introduced a new challenge…
Exfiltration of data via email is a serious cybersecurity threat for many organizations. Detecting data exfiltration (anomaly) patterns typically requires labeling, most often done by a human annotator, to reduce the high number of false…
An increasing number of artificial intelligence (AI) applications involve the execution of deep neural networks (DNNs) on edge devices. Many practical reasons motivate the need to update the DNN model on the edge device post-deployment,…
Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is…
Bayesian inference on non-Gaussian data is often non-analytic and requires computationally expensive approximations such as sampling or variational inference. We propose an approximate inference framework primarily designed to be…
In this work we explore a straightforward variational Bayes scheme for Recurrent Neural Networks. Firstly, we show that a simple adaptation of truncated backpropagation through time can yield good quality uncertainty estimates and superior…
One of the fundamental limitations of Deep Neural Networks (DNN) is its inability to acquire and accumulate new cognitive capabilities. When some new data appears, such as new object classes that are not in the prescribed set of objects…
The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of…
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally…
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework,…
Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of…
Majorly classical Active Learning (AL) approach usually uses statistical theory such as entropy and margin to measure instance utility, however it fails to capture the data distribution information contained in the unlabeled data. This can…
Batch active learning (BAL) is a crucial technique for reducing labeling costs and improving data efficiency in training large-scale deep learning models. Traditional BAL methods often rely on metrics like Mahalanobis Distance to balance…
Varying annotation costs among data points and budget constraints can hinder the adoption of active learning strategies in real-world applications. This work introduces two Bayesian active learning strategies for batch acquisition under…
Numerical integration and emulation are fundamental topics across scientific fields. We propose novel adaptive quadrature schemes based on an active learning procedure. We consider an interpolative approach for building a surrogate…