Related papers: In-memory phononic learning toward cognitive mecha…

Multimodal learning enhances the perceptual capabilities of cognitive systems by integrating information from different sensory modalities. However, existing multimodal fusion research typically assumes static integration, not fully…

The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neuroscience (aka. engrams)…

Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…

The concept of topological energy bands and their manifestations have been demonstrated in condensed matter systems as a fantastic paradigm toward unprecedented physical phenomena and properties that are robust against disorders. Recent…

A holistic understanding of object properties across diverse sensory modalities (e.g., visual, audio, and haptic) is essential for tasks ranging from object categorization to complex manipulation. Drawing inspiration from cognitive science…

Foundation models are transforming neuroscience but are often prohibitively large, data-hungry, and difficult to deploy. Here, we introduce BrainSymphony, a lightweight and parameter-efficient foundation model with plug-and-play integration…

Communications are realized as a result of successive decisions at the physical layer, from modulation selection to multi-antenna strategy, and each decision affects the performance of the communication systems. Future communication systems…

How can one design complex systems capable of learning for a given functionality? In the context of ultrafast laser-surface interaction, we unravel the nature of learning schemes tied to the emergence of complexity in dissipative…

Traveling waves of neural activity are widely observed in the brain, but their precise computational function remains unclear. One prominent hypothesis is that they enable the transfer and integration of spatial information across neural…

In recent years, remarkable advances in photonic computing have highlighted the need for photonic memory, particularly high-speed and coherent random-access memory. Addressing the ongoing challenge of implementing photonic memories is…

Multimodal learning aims to enhance perceptual and decision-making capabilities by integrating information from diverse sources. However, classical deep learning approaches face a critical trade-off between the high accuracy of black-box…

Despite the promise of superior efficiency and scalability, real-world deployment of emerging nanoelectronic platforms for brain-inspired computing have been limited thus far, primarily because of inter-device variations and intrinsic…

Representation learning is a fundamental building block for analyzing entities in a database. While the existing embedding learning methods are effective in various data mining problems, their applicability is often limited because these…

Emerging wearable devices such as smartglasses and extended reality headsets demand high-quality spatial audio capture from compact, head-worn microphone arrays. Ambisonics provides a device-agnostic spatial audio representation by mapping…

Memory, understood as time non-locality, is a fundamental property of any physical system, whether classical or quantum, and has important applications in a wide variety of technologies. In the context of quantum technologies, systems with…

Over the past decade inter-atomic potentials based on machine-learning (ML) techniques have become an indispensable tool in the atomic-scale modeling of materials. Trained on energies and forces obtained from electronic-structure…

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

The complex world around us is inherently multimodal and sequential (continuous). Information is scattered across different modalities and requires multiple continuous sensors to be captured. As machine learning leaps towards better…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…