Related papers: Self-Regulated Neurogenesis for Online Data-Increm…

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to…

A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this paradigm is commonly made possible through experience replay,…

Although depth extraction with passive sensors has seen remarkable improvement with deep learning, these approaches may fail to obtain correct depth if they are exposed to environments not observed during training. Online adaptation, where…

Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…

This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we…

Cell type identification from single-cell transcriptomic data is a common goal of single-cell RNA sequencing (scRNAseq) data analysis. Neural networks have been employed to identify cell types from scRNAseq data with high performance.…

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a…

Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive hidden state resets. However, reset-based methods impose…

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains…

In a conventional supervised learning setting, a machine learning model has access to examples of all object classes that are desired to be recognized during the inference stage. This results in a fixed model that lacks the flexibility to…

This paper investigates continual learning for semantic parsing. In this setting, a neural semantic parser learns tasks sequentially without accessing full training data from previous tasks. Direct application of the SOTA continual learning…

Contemporary approaches to instance segmentation in cell science use 2D or 3D convolutional networks depending on the experiment and data structures. However, limitations in microscopy systems or efforts to prevent phototoxicity commonly…

Concept drift and extreme verification latency pose significant challenges in data stream learning, particularly when dealing with recurring concept changes in dynamic environments. This work introduces a novel method based on the Growing…

The nervous system, more specifically, the brain, is capable of solving complex problems simply and efficiently, far surpassing modern computers. In this regard, neuromorphic engineering is a research field that focuses on mimicking the…

The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones,…

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a…

Humans and animals can learn new skills after practicing for a few hours, while current reinforcement learning algorithms require a large amount of data to achieve good performances. Recent model-based approaches show promising results by…