Related papers: Dendritic Self-Organizing Maps for Continual Learn…

Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learning. The impetus for a paradigm shift in how hardware is used for computational intelligence stems…

The digital age has completely transformed the way that information is processed and stored, which makes cybersecurity a crucial field of research. Cybersecurity contains many different domains, but this work focuses on Intrusion Detection…

In lifelong learning systems based on artificial neural networks, one of the biggest obstacles is the inability to retain old knowledge as new information is encountered. This phenomenon is known as catastrophic forgetting. In this paper,…

Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later…

In many research fields, the sizes of the existing datasets vary widely. Hence, there is a need for machine learning techniques which are well-suited for these different datasets. One possible technique is the self-organizing map (SOM), a…

Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear…

Results of neural network learning are always subject to some variability, due to the sensitivity to initial conditions, to convergence to local minima, and, sometimes more dramatically, to sampling variability. This paper presents a set of…

Density-equalizing map (DEM) serves as a powerful technique for creating shape deformations with the area changes reflecting an underlying density function. In recent decades, DEM has found widespread applications in fields such as data…

In many real world applications, data cannot be accurately represented by vectors. In those situations, one possible solution is to rely on dissimilarity measures that enable sensible comparison between observations. Kohonen's…

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…

Controlling the internal representation space of a neural network is a desirable feature because it allows to generate new data in a supervised manner. In this paper we will show how this can be achieved while building a low-dimensional…

In numerous applicative contexts, data are too rich and too complex to be represented by numerical vectors. A general approach to extend machine learning and data mining techniques to such data is to really on a dissimilarity or on a kernel…

Deep Neural Networks (DNNs) have two key deficiencies, their dependence on high precision computing and their inability to perform sequential learning, that is, when a DNN is trained on a first task and the same DNN is trained on the next…

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

Topographic feature maps are low dimensional representations of data, that preserve spatial dependencies. Current methods of training such maps (e.g. self organizing maps - SOM, generative topographic maps) require centralized control and…

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an…

Developing an effective automatic classifier to separate genuine sources from artifacts is essential for transient follow-ups in wide-field optical surveys. The identification of transient detections from the subtraction artifacts after the…

Recent progress in the fields of AI and cognitive sciences opens up new challenges that were previously inaccessible to study. One of such modern tasks is recovering lost data of one modality by using the data from another one. A similar…

Recent advances in object detection have benefited significantly from rapid developments in deep neural networks. However, neural networks suffer from the well-known issue of catastrophic forgetting, which makes continual or lifelong…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…