Related papers: Towards Lateral Inhibition and Collective Percepti…
Lateral Inhibition (LI) phenomena occur in a wide range of sensory modalities and are most famously described in the human visual system. In LI the activity of a stimulated neuron is itself excited and suppresses the activity of its local…
Very simple organisms, such as the single-celled amoeboid slime mould Physarum polycephalum possess no neural tissue yet, despite this, are known to exhibit complex biological and computational behaviour. Given such limited resources, can…
True slime mould Physarum polycephalum approximates a range of complex computations via growth and adaptation of its proto- plasmic transport network, stimulating a large body of recent research into how such a simple organism can perform…
Simplicial complexes prove effective in modeling data with multiway dependencies, such as data defined along the edges of networks or within other higher-order structures. Their spectrum can be decomposed into three interpretable subspaces…
Building mathematical models of brains is difficult because of the sheer complexity of the problem. One potential starting point is through basal cognition, which gives abstract representation of a range of organisms without central nervous…
Collective movement occurs in living systems where the simple movements of individual members of a pop- ulation are combined to generate movement of the collective as a whole, displaying complex dynamics which cannot be found in the…
How do non-neural organisms, such as the slime mould \textit{Physarum polycephalum}, anticipate periodic events in their environment? We present a minimal, biologically inspired reservoir model that demonstrates simple temporal anticipation…
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow…
Biological brains learn continually from a stream of unlabeled data, while integrating specialized information from sparsely labeled examples without compromising their ability to generalize. Meanwhile, machine learning methods are…
Self-assembled structures are possible solutions to the problem of increasing the density and connectivity of memristive units in massive arrays. Although they would allow surpassing the limit imposed by the lithographic feature size, the…
The backpropagation method has enabled transformative uses of neural networks. Alternatively, for energy-based models, local learning methods involving only nearby neurons offer benefits in terms of decentralized training, and allow for the…
Multi-modal affective computing aims to automatically recognize and interpret human attitudes from diverse data sources such as images and text, thereby enhancing human-computer interaction and emotion understanding. Existing approaches…
Inhibition is considered to shape neural activity, and broaden its pattern repertoire. In the sensory organs, where the anatomy of neural circuits is highly structured, lateral inhibition sharpens contrast among stimulus properties. The…
Adaptive response to a varying environment is a common feature of biological organisms. Reproducing such features in electronic systems and circuits is of great importance for a variety of applications. Here, we consider memory models…
The slime mould Physarum polycephalum has been used in developing unconventional computing devices for in which the slime mould played a role of a sensing, actuating, and computing device. These devices treated the slime mould rather as an…
Associative learning is one of the key mechanisms displayed by living organisms in order to adapt to their changing environments. It was early recognized to be a general trait of complex multicellular organisms but also found in "simpler"…
The dielectric behavior of a linear cluster of two or more living cells connected by tight junctions is analyzed using a spectral method. The polarizability of this system is obtained as an expansion over the eigenmodes of the linear…
Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images. In this paper, we respond to the intriguing learning-related question -- if leveraging…
Large language models (LLMs) have emerged as powerful general-purpose interfaces for many machine learning problems. Recent work has adapted LLMs to generative visual tasks like image captioning, visual question answering, and visual chat,…
Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalities. This convergence is predictive of alignment with brain representation. A recent…