23 papers · ranked by Valyu relevance
I. Cone, H. Z. Shouval
The ability to express and learn temporal sequences is an essential part of learning and memory. Learned temporal sequences are expressed in multiple brain regions and as such there may be common design in the circuits that mediate it. This work proposes a substrate for such representations, via a biophysically…
Kristjan Kalm, Dennis Norris, Ronald van den Berg
We contrast two computational models of sequence learning. The associative learner posits that learning proceeds by strengthening existing association weights. Alternatively, recoding posits that learning creates new and more efficient representations of the learned sequences. Importantly, both models propose that…
Clive R. Rosenthal, Christopher Kennard, David Soto, Edwin Robertson
Background The ability to detect and integrate associations between unrelated items that are close in space and time is a key feature of human learning and memory. Learning sequential associations between non-adjacent visual stimuli (higher-order visuospatial dependencies) can occur either with or without awareness…
Kaede Kido, Shogo Makioka
It is widely known that statistical learning of visual symbol sequences occurs implicitly ([14]). In this study, we examined whether people can learn the serial order of visual symbols when they cannot detect them. During the familiarization phase, triplets or quadruplets of novel symbols were presented to one eye…
Ting Yao, Yiheng Zhang, Zhaofan Qiu, Yingwei Pan + 1 more
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised…
Clive R. Rosenthal, Tammy W. C. Ng, Christopher Kennard, Edwin Robertson
'Edwin Robertson'] New visuomotor skills can guide behaviour in novel situations. Prior studies indicate that learning a visuospatial sequence via responses based on manual key presses leads to effector- and response-independent knowledge. Little is known, however, about the extent to which new sequence knowledge can…
Yiren Ren, Vishwadeep Ahluwalia, Claire Arthur, Thackery Brown
Statistical learning—the ability to extract patterns from noisy continuous experiences—is fundamental to human cognition. Yet, how contextual factors shape this process remains poorly understood. Music is an important example of such contextual factors, because it is ubiquitous in human experience and provides a rich…
Viacheslav Osaulenko
In this paper we start with a simple question, how is it possible that humans can recognize different movements over skin with only a prior visual experience of them? Or in general, what is the representation of spatial sequences that are invariant to scale, rotation, and translation across different modalities? To…
Kristjan Kalm, Dennis Norris
We contrast two accounts of how novel sequences are learned. The first is that learning changes the signal-to-noise ratio (SNR) of existing neural representations by reducing noise or increasing signal gain. Alternatively, learning might cause the initial representation of the sequence to be recoded into more efficient…
Charlotte Volk, Christopher C. Pack, Shahab Bakhtiari
Generalization of visual perceptual learning (VPL) to unseen conditions varies across tasks. Previous work suggests that training curriculum may be integral to generalization, yet a theoretical explanation is lacking. We propose an explanatory theory of visual learning generalization and curriculum effects by…
Xianhui He, Philipp K. Büchel, Simon Faghel-Soubeyrand, Janina Klingspohr + 2 more
Experiences reshape our internal representations of the world. However, the neural and cognitive dynamics of this process are largely unknown. Here, we investigated how sequence learning reorganizes neural representations and how sleep-dependent consolidation contributes to this transformation. Using high-density…
Qiong Liu, Yanxia Zhang
—As data from IoT (Internet of Things) sensors become ubiquitous, state-of-the-art machine learning algorithms face many challenges on directly using sensor data. To overcome these challenges, methods must be designed to learn directly from sensors without manual annotations. This paper introduces Sensory Time-cue for…
Yuwei Cui, Subutai Ahmad, Jeff Hawkins
The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory is recently proposed as a theoretical framework for sequence learning in the cortex. In this…
Riccardo Mereu, Gabriele Trivigno, Gabriele Berton, Carlo Masone + 1 more
'Barbara Caputo'] Abstract— In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known places. This task requires robust, scalable, and efficient techniques for real applications. This work proposes a…
Tejas Savalia, Anuj Shukla, Raju S. Bapi
The capacity to sequence information is central to human performance. Sequencing ability forms the foundation stone for higher order cognition related to language and goal-directed planning. Information related to the order of items, their timing, chunking and hierarchical organization are important aspects in…
M. Zhao, Chengxu Zhuang, Yizhou Wang, Tai Sing Lee
We propose a new neurally-inspired model that can learn to encode the global relationship context of visual events across time and space and to use the contextual information to modulate the analysis by synthesis process in a predictive coding framework. The model learns latent contextual representations by maximizing…
Matthew Farrell, Cengiz Pehlevan
Understanding how neural circuits generate sequential activity is a longstanding challenge. While foundational theoretical models have shown how sequences can be stored as memories with Hebbian plasticity rules, these models considered only a narrow range of Hebbian rules. Here we introduce a model for arbitrary…
Vadym Gryshchuk, Cornelius Weber, Chu Kiong Loo, Stefan Wermter
Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for learning from data produced by event cameras and compare techniques to mitigate…
Michael R Bale, Malamati Bitzidou, Anna Pitas, Leonie S Brebner + 5 more
'Lina Khazim' 'Stavros T Anagnou' 'Caitlin D Stevenson' 'Miguel Maravall' 'Ranulfo Romo'] The world around us is replete with stimuli that unfold over time. When we hear an auditory stream like music or speech or scan a texture with our fingertip, physical features in the stimulus are concatenated in a particular…
Authors not listed
This research presents a novel approach to obstacle detection during navigation using a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The primary objective is to generate accurate image captions that describe the content of images, which is crucial for applications such…
Hang Hu, Jyothsna Padmakumar Bindu, Julia Laskin
Mass spectrometry imaging (MSI) is widely used for the label-free molecular mapping of biological samples. The identification of co-localized molecules in MSI data is crucial to the understanding of biochemical pathways. However, complex MSI data are too large for manual annotation but too small for training deep…
Authors not listed
Molecular property prediction is a fundamental task in computational chemistry with critical applications in drug discovery and materials science. While recent works have explored Large Language Models (LLMs) for this task, they primarily rely on textual molecular representations such as SMILES/SELFIES, which can be…
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…