Search · four archives
Search · four archives
23 papers · ranked by Valyu relevance
Thomas Miconi, Michael J Frank
Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are…
Alexandra R. van den Berg, Pieter R. Roelfsema, Sander M. Bohte
The acquisition of knowledge does not occur in isolation; rather, learning experiences in the same or similar domains amalgamate. This process through which learning can accelerate over time is referred to as learning-to-learn or meta-learning. While meta-learning can be implemented in recurrent neural networks, these…
Thomas Miconi
Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Recurrent neural networks operating in the near-chaotic regime, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing…
Kamil Rocki
There exists a theory of a single general-purpose learning algorithm which could explain the principles its operation. It assumes the initial rough architecture, a small library of simple innate circuits which are prewired at birth. and proposes that all significant mental algorithms are learned. Given current…
Geunbo Yang, Wongyu Lee, Youjung Seo, Choongseop Lee + 5 more
'Jongkil Park' 'Donggyu Sim' 'Cheolsoo Park' 'Richard J. Povinelli'] A spiking neural network (SNN) is a type of artificial neural network that operates based on discrete spikes to process timing information, similar to the manner in which the human brain processes real-world problems. In this paper, we propose a new…
Eric C. Wong
In this hypothesis paper we argue that when driven by example behavior, a simple Hebbian learning mechanism can form the core of a computational theory of learning that can support both low level learning and the development of human level intelligence. We show that when driven by example behavior Hebbian learning…
Yoshimasa Kubo, Eric Chalmers, Artur Luczak
Backpropagation (BP) has been used to train neural networks for many years, allowing them to solve a wide variety of tasks like image classification, speech recognition, and reinforcement learning tasks. But the biological plausibility of BP as a mechanism of neural learning has been questioned. Equilibrium Propagation…
Magdalena Kozielska, Franz J. Weissing
The ability to learn from past experience is an important adaptation, but how natural selection shapes learning is not well understood. Here, we present a novel way of modelling learning using small neural networks and a simple, biology-inspired learning algorithm. Learning affects only part of the network, and it is…
Yuhao Sun, Wantong Liao, Jinhao Li, Xinche Zhang + 3 more
'Zhiyuan Ma' 'Sen Song'] Synaptic plasticity underlies adaptive learning in neural systems, offering a biologically plausible framework for reward-driven learning. However, a question remains: how can plasticity rules achieve robustness and effectiveness comparable to error backpropagation? In this study, we introduce…
Wayne W.M. Soo, Vishwa Goudar, Xiao-Jing Wang
Training recurrent neural networks (RNNs) has become a go-to approach for generating and evaluating mechanistic neural hypotheses for cognition. The ease and efficiency of training RNNs with backpropagation through time and the availability of robustly supported deep learning libraries has made RNN modeling more…
Markus Meister
Animals can learn efficiently from a single experience and change their future behavior in response. However, in other instances, animals learn very slowly, requiring thousands of experiences. Here I survey tasks involving fast and slow learning and consider some hypotheses for what differentiates the underlying neural…
Blake Bordelon, Cengiz Pehlevan
The brain can learn from a limited number of experiences, an ability which requires suitable built in assumptions about the nature of the tasks which must be learned, or inductive biases. While inductive biases are central components of intelligence, how they are reflected in and shaped by population codes are not…
Linnie Jiang, Ashok Litwin-Kumar, Abigail Morrison
The Drosophila mushroom body exhibits dopamine dependent synaptic plasticity that underlies the acquisition of associative memories. Recordings of dopamine neurons in this system have identified signals related to external reinforcement such as reward and punishment. However, other factors including locomotion…
Birgitta Dresp
This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the…
Samuel J Gershman, Petra EM Balbi, C Randy Gallistel, Jeremy Gunawardena + 2 more
'Jeremy Gunawardena' 'Laura L Colgin' 'Laura L Colgin'] The question of whether single cells can learn led to much debate in the early 20th century. The view prevailed that they were capable of non-associative learning but not of associative learning, such as Pavlovian conditioning. Experiments indicating the contrary…
Marcelo G. Mattar, Danielle S. Bassett
Human learning is a complex phenomenon that requires adaptive processes across a range of temporal and spacial scales. While our understanding of those processes at single scales has increased exponentially over the last few years, a mechanistic understanding of the entire phenomenon has remained elusive. We propose…
Bjöern Brembs
In contrast to the long-held assumption that the organization of behavior is best characterized as the perception of a sensory stimulus followed by appropriate response (i.e., “sensorimotor hypothesis”), recent converging evidence from multiple systems and fields of study instead suggests that both ancestral and extant…
Colin Bredenberg, Cristina Savin
Normative models of synaptic plasticity use a combination of mathematics and computational simulations to arrive at predictions of behavioral and network-level adaptive phenomena. In recent years, there has been an explosion of theoretical work on these models, but experimental confirmation is relatively limited. In…
Colin Bredenberg, Cristina Savin
Normative models of synaptic plasticity use a combination of mathematics and computational simulations to arrive at predictions of behavioral and network-level adaptive phenomena. In recent years, there has been an explosion of theoretical work on these models, but experimental confirmation is relatively limited. In…
Authors not listed
The use of hybrid models, combing mechanistic and machine learning (ML), has emerged as a promising approach, contributing to the development of Industry 4.0. This work presents a hybrid model that forecasts minibioreactor (MBR) production runs of mammalian cell culture recombinant for monoclonal antibodies (mAbs)…
Authors not listed
Predicting drug-induced toxicity remains a central challenge in computational toxicology, particularly for organ-specific adverse effects that arise from diverse structural, biochemical, and mechanistic origins. Existing deep learning models excel at pattern recognition but often lack mechanistic interpretability…
Authors not listed
In recent years, generative deep learning has emerged as a transformative approach in drug design, promising to explore the vast chemical space and generate novel molecules with desired biological properties. This perspective examines the challenges and opportunities of applying generative models to drug discovery…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…