Related papers: SatSOM: Saturation Self-Organizing Maps for Contin…

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the…

We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with…

Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…

Some argue that biologically inspired algorithms are the future of solving difficult problems in computer science. Others strongly believe that the future lies in the exploration of mathematical foundations of problems at hand. The field of…

Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly…

We propose a unified view on two widely used data visualization techniques: Self-Organizing Maps (SOMs) and Stochastic Neighbor Embedding (SNE). We show that they can both be derived from a common mathematical framework. Leveraging this…

For long-term simultaneous planning, localization and mapping (SPLAM), a robot should be able to continuously update its map according to the dynamic changes of the environment and the new areas explored. With limited onboard computation…

We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improves generalization…

Continual learning is a key feature of biological neural systems, but artificial neural networks often suffer from catastrophic forgetting. Instead of backpropagation, biologically plausible learning algorithms may enable stable continual…

The increasing maturity of big data applications has led to a proliferation of models targeting the same objectives within the same scenarios and datasets. However, selecting the most suitable model that considers model's features while…

We proposed an end-to-end deep learning-based simultaneous localization and mapping (SLAM) system following conventional visual odometry (VO) pipelines. The proposed method completes the SLAM framework by including tracking, mapping, and…

This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in continual reinforcement learning. The structure of each module allows the selective combination of…

The field of artificial intelligence has significantly advanced over the past decades, inspired by discoveries from the fields of biology and neuroscience. The idea of this work is inspired by the process of self-organization of cortical…

Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…

The challenge of fine-grained visual recognition often lies in discovering the key discriminative regions. While such regions can be automatically identified from a large-scale labeled dataset, a similar method might become less effective…

This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the…

A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts. While the recent progress in continual…

Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and often causes catastrophic forgetting issue when learning…

Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization problems and over-parametrization. In the present work, we propose a new syntax-aware language model:…