Biological Cybernetics最新文献

{"title":"Canonical circuit computations for computer vision.","authors":"Daniel Schmid, Christian Jarvers, Heiko Neumann","doi":"10.1007/s00422-023-00966-9","DOIUrl":"10.1007/s00422-023-00966-9","url":null,"abstract":"<p><p>Advanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advances in machine vision. We propose to utilize structural and functional principles of neural systems that have been largely overlooked. They potentially provide new inspirations for computer vision mechanisms and models. Recurrent feedforward, lateral, and feedback interactions characterize general principles underlying processing in mammals. We derive a formal specification of core computational motifs that utilize these principles. These are combined to define model mechanisms for visual shape and motion processing. We demonstrate how such a framework can be adopted to run on neuromorphic brain-inspired hardware platforms and can be extended to automatically adapt to environment statistics. We argue that the identified principles and their formalization inspires sophisticated computational mechanisms with improved explanatory scope. These and other elaborated, biologically inspired models can be employed to design computer vision solutions for different tasks and they can be used to advance neural network architectures of learning.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"299-329"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9613848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bio-inspired, task-free continual learning through activity regularization.","authors":"Francesco Lässig,&nbsp;Pau Vilimelis Aceituno,&nbsp;Martino Sorbaro,&nbsp;Benjamin F Grewe","doi":"10.1007/s00422-023-00973-w","DOIUrl":"10.1007/s00422-023-00973-w","url":null,"abstract":"<p><p>The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning (CL) approaches have been devised. However, these usually require discrete task boundaries. This requirement seems biologically implausible and often limits the application of CL methods in the real world where tasks are not always well defined. Here, we take inspiration from neuroscience, where sparse, non-overlapping neuronal representations have been suggested to prevent catastrophic forgetting. As in the brain, we argue that these sparse representations should be chosen on the basis of feed forward (stimulus-specific) as well as top-down (context-specific) information. To implement such selective sparsity, we use a bio-plausible form of hierarchical credit assignment known as Deep Feedback Control (DFC) and combine it with a winner-take-all sparsity mechanism. In addition to sparsity, we introduce lateral recurrent connections within each layer to further protect previously learned representations. We evaluate the new sparse-recurrent version of DFC on the split-MNIST computer vision benchmark and show that only the combination of sparsity and intra-layer recurrent connections improves CL performance with respect to standard backpropagation. Our method achieves similar performance to well-known CL methods, such as Elastic Weight Consolidation and Synaptic Intelligence, without requiring information about task boundaries. Overall, we showcase the idea of adopting computational principles from the brain to derive new, task-free learning algorithms for CL.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"345-361"},"PeriodicalIF":1.9,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600047/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10014353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stakes of neuromorphic foveation: a promising future for embedded event cameras.","authors":"Amélie Gruel,&nbsp;Dalia Hareb,&nbsp;Antoine Grimaldi,&nbsp;Jean Martinet,&nbsp;Laurent Perrinet,&nbsp;Bernabé Linares-Barranco,&nbsp;Teresa Serrano-Gotarredona","doi":"10.1007/s00422-023-00974-9","DOIUrl":"10.1007/s00422-023-00974-9","url":null,"abstract":"<p><p>Foveation can be defined as the organic action of directing the gaze towards a visual region of interest to acquire relevant information selectively. With the recent advent of event cameras, we believe that taking advantage of this visual neuroscience mechanism would greatly improve the efficiency of event data processing. Indeed, applying foveation to event data would allow to comprehend the visual scene while significantly reducing the amount of raw data to handle. In this respect, we demonstrate the stakes of neuromorphic foveation theoretically and empirically across several computer vision tasks, namely semantic segmentation and classification. We show that foveated event data have a significantly better trade-off between quantity and quality of the information conveyed than high- or low-resolution event data. Furthermore, this compromise extends even over fragmented datasets. Our code is publicly available online at: https://github.com/amygruel/FoveationStakes_DVS .</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"389-406"},"PeriodicalIF":1.9,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41154519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Periodic solutions in next generation neural field models.","authors":"Carlo R Laing, Oleh E Omel'chenko","doi":"10.1007/s00422-023-00969-6","DOIUrl":"10.1007/s00422-023-00969-6","url":null,"abstract":"<p><p>We consider a next generation neural field model which describes the dynamics of a network of theta neurons on a ring. For some parameters the network supports stable time-periodic solutions. Using the fact that the dynamics at each spatial location are described by a complex-valued Riccati equation we derive a self-consistency equation that such periodic solutions must satisfy. We determine the stability of these solutions, and present numerical results to illustrate the usefulness of this technique. The generality of this approach is demonstrated through its application to several other systems involving delays, two-population architecture and networks of Winfree oscillators.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"259-274"},"PeriodicalIF":1.7,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600056/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9981808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Bcm rule allows a spinal cord model to learn rhythmic movements.","authors":"Matthias Kohler,&nbsp;Florian Röhrbein,&nbsp;Alois Knoll,&nbsp;Alin Albu-Schäffer,&nbsp;Henrik Jörntell","doi":"10.1007/s00422-023-00970-z","DOIUrl":"10.1007/s00422-023-00970-z","url":null,"abstract":"<p><p>Currently, it is accepted that animal locomotion is controlled by a central pattern generator in the spinal cord. Experiments and models show that rhythm generating neurons and genetically determined network properties could sustain oscillatory output activity suitable for locomotion. However, current central pattern generator models do not explain how a spinal cord circuitry, which has the same basic genetic plan across species, can adapt to control the different biomechanical properties and locomotion patterns existing in these species. Here we demonstrate that rhythmic and alternating movements in pendulum models can be learned by a monolayer spinal cord circuitry model using the Bienenstock-Cooper-Munro learning rule, which has been previously proposed to explain learning in the visual cortex. These results provide an alternative theory to central pattern generator models, because rhythm generating neurons and genetically defined connectivity are not required in our model. Though our results are not in contradiction to current models, as existing neural mechanism and structures, not used in our model, can be expected to facilitate the kind of learning demonstrated here. Therefore, our model could be used to augment existing models.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"275-284"},"PeriodicalIF":1.9,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10078177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Extreme image transformations affect humans and machines differently.","authors":"Girik Malik,&nbsp;Dakarai Crowder,&nbsp;Ennio Mingolla","doi":"10.1007/s00422-023-00968-7","DOIUrl":"10.1007/s00422-023-00968-7","url":null,"abstract":"<p><p>Some recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evaluate humans and ANNs on an object recognition task. We show that machines perform better than humans for certain transforms and struggle to perform at par with humans on others that are easy for humans. We quantify the differences in accuracy for humans and machines and find a ranking of difficulty for our transforms for human data. We also suggest how certain characteristics of human visual processing can be adapted to improve the performance of ANNs for our difficult-for-machines transforms.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"331-343"},"PeriodicalIF":1.9,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600046/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9622333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis.","authors":"Michael Briden,&nbsp;Narges Norouzi","doi":"10.1007/s00422-023-00967-8","DOIUrl":"10.1007/s00422-023-00967-8","url":null,"abstract":"<p><p>We propose a subject-aware contrastive learning deep fusion neural network framework for effectively classifying subjects' confidence levels in the perception of visual stimuli. The framework, called WaveFusion, is composed of lightweight convolutional neural networks for per-lead time-frequency analysis and an attention network for integrating the lightweight modalities for final prediction. To facilitate the training of WaveFusion, we incorporate a subject-aware contrastive learning approach by taking advantage of the heterogeneity within a multi-subject electroencephalogram dataset to boost representation learning and classification accuracy. The WaveFusion framework demonstrates high accuracy in classifying confidence levels by achieving a classification accuracy of 95.7% while also identifying influential brain regions.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":" ","pages":"363-372"},"PeriodicalIF":1.9,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600301/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10106597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Teaching Method In Writing Descriptive Text (A Descriptive Study at the Seventh Grade Students of Thammislam Foundation School Academic Year 2023)","authors":"Fahri Akbar, Pirman Ginting","doi":"10.51178/cjerss.v4i3.1521","DOIUrl":"https://doi.org/10.51178/cjerss.v4i3.1521","url":null,"abstract":"&#x0D; &#x0D; &#x0D; &#x0D; This study investigates the instructional approach English teachers employ in teaching descriptive writing to seventh-grade students at Thammislam Foundation School during the Academic Year 2023. What challenges does the English teacher encounter when instructing seventh-grade students at Thammislam Foundation School during the Academic Year 2023 in the area of writing descriptive texts? The research objectives are categorized into three distinct areas: writing, descriptive text, and the instructional methods employed by English teachers. The present study employed a descriptive qualitative research design. The researcher assumed the role of a non-participant observer. The researcher conducted three observations in a seventh-grade classroom and interviewed with an English teacher to gather information about the instructional methods employed in teaching descriptive writing. The observed population comprises 28 students enrolled in the seventh grade at Thammislam Foundation School during the academic year of 2023. The data collection instruments employed in this study encompassed observation, interviews, and the examination of relevant study documents, including modules, student worksheets, and curriculum materials. The researcher employed a three-step process to analyze the data. The three main components of the research process include data reduction, data display, and conclusion verification. Researchers employ triangulation as a means to enhance the trustworthiness of the data. The research findings indicate that the activities conducted by the teacher during the initial and subsequent meetings were consistent with the principles and framework of task-based language teaching. Implementing task-based language teaching in a classroom typically involves three distinct stages: the pre-task stage, the task cycle, and the language focus stage. The challenges encountered by the student included a limited vocabulary and a need for more proficiency in selecting appropriate verbs for constructing sentences. The instructor assigned exercises to enhance the students' vocabulary and proficiency in selecting the appropriate verb for each sentence. The models used for the tasks were evaluated based on their ability to match the given criteria accurately. In addition, the instructor employed a systematic approach to facilitate comprehension among the students, particularly in the context of composing descriptive texts.&#x0D; &#x0D; &#x0D; &#x0D;","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":"353 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135255768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Communication Barriers Between EFL Indonesian Teachers and EFL Learners in Thammislam Foundation School, Thailand","authors":"Viga Kumala, Pirman Ginting","doi":"10.51178/cjerss.v4i3.1508","DOIUrl":"https://doi.org/10.51178/cjerss.v4i3.1508","url":null,"abstract":"English communication barriers are a circumstance that EFL learners frequently experience. This problem is not limited to situations, people and time. The educational field is not an exception, furthermore, here is where the basis for English language learning for EFL students is formed. Lack of communication is nothing new felt by both sides. In regard to that topic, this research presents the communication barrier issue, which the writer, an EFL teacher, observed and encountered toward EFL learners when carrying out teaching and learning activities at Thammislam Foundation School in Thailand. This study aims to identify the various categories of issues that arise when interacting using English and to provide solutions or suggestions to these problems which are expected to help in the future event. The data of this study were collected in two ways, using a questionnaire and doing an interview with a total of 13 participants. The result indicates that the Disinterest factor shows up as the highest that caused communication barriers with a percentage of 22.3% while the Sosio-attitudinal factor is the lowest with a percentage of 19%.","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":"861 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134972044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-organizing maps on \"what-where\" codes towards fully unsupervised classification.","authors":"Luis Sa-Couto,&nbsp;Andreas Wichert","doi":"10.1007/s00422-023-00963-y","DOIUrl":"https://doi.org/10.1007/s00422-023-00963-y","url":null,"abstract":"<p><p>Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":"117 3","pages":"211-220"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10258173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9616983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}