Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Exploring the associative learning capabilities of the segmented attractor network for lifelong learning.

ABSTRACT: This work explores the process of adapting the segmented attractor network to a lifelong learning setting. Taking inspirations from Hopfield networks and content-addressable memory, the segmented attractor network is a powerful tool for associative memory applications. The network's performance as an associative memory is analyzed using multiple metrics. In addition to the network's general hit rate, its capability to recall unique memories and their frequency is also evaluated with respect to time. Finally, additional learning techniques are implemented to enhance the network's recall capacity in the application of lifelong learning. These learning techniques are based on human cognitive functions such as memory consolidation, prediction, and forgetting.

SUBMITTER: Jones A

PROVIDER: S-EPMC9376266 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Exploring the associative learning capabilities of the segmented attractor network for lifelong learning.

Jones Alexander A Jha Rashmi R

Frontiers in artificial intelligence 20220801

This work explores the process of adapting the segmented attractor network to a lifelong learning setting. Taking inspirations from Hopfield networks and content-addressable memory, the segmented attractor network is a powerful tool for associative memory applications. The network's performance as an associative memory is analyzed using multiple metrics. In addition to the network's general hit rate, its capability to recall unique memories and their frequency is also evaluated with respect to t ...[more]

PMID: 35978653

Similar Datasets

Differential expression: associative and nonassociative learning

Project description:Hippocamus and amygdala expression was examined in naïve, conditioned stimulus exposed, and fear conditioned mice 30 minutes after behavioral manipulation Keywords: comparison of 3 groups x 2 brain regions

2006-03-20 | GSE3963 | GEO

Exploring deep learning capabilities for surge predictions in coastal areas.

Project description:To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on local atmospheric conditions. We use an Artificial Neural Networks, Convolutional Neural Network, Long Short-Term Memory layer (LSTM) and a combination of the latter two (ConvLSTM), to construct ensembles of Neural Network (NN) models at 736 tide stations globally. The NN models show similar patterns of performance, with much higher skill in the mid-latitudes. Using our global model settings, the LSTM generally outperforms the other NN models. Furthermore, for 15 stations we assess the influence of adding complexity more predictor variables. This generally improves model performance but leads to substantial increases in computation time. The improvement in performance remains insufficient to fully capture observed dynamics in some regions. For example, in the tropics only modelling surges is insufficient to capture intra-annual sea level variability. While we focus on minimising mean absolute error for the full time series, the NN models presented here could be adapted for use in forecasting extreme sea levels or emergency response.

| S-EPMC8390491 | biostudies-literature

On stability and associative recall of memories in attractor neural networks.

Project description:Attractor neural networks such as the Hopfield model can be used to model associative memory. An efficient associative memory should be able to store a large number of patterns which must all be stable. We study in detail the meaning and definition of stability of network states. We reexamine the meanings of retrieval, recognition and recall and assign precise mathematical meanings to each of these terms. We also examine the relation between them and how they relate to memory capacity of the network. We have shown earlier in this journal that orthogonalization scheme provides an effective way of overcoming catastrophic interference that limits the memory capacity of the Hopfield model. It is not immediately apparent whether the improvement made by orthgonalization affects the processes of retrieval, recognition and recall equally. We show that this influence occurs to different degrees and hence affects the relations between them. We then show that the conditions for pattern stability can be split into a necessary condition (recognition) and a sufficient one (recall). We interpret in cognitive terms the information being stored in the Hopfield model and also after it is orthogonalized. We also study the alterations in the network dynamics of the Hopfield network upon the introduction of orthogonalization, and their effects on the efficiency of the network as an associative memory.

| S-EPMC7498056 | biostudies-literature

Exploring attractor bifurcations in Boolean networks.

Project description:BackgroundBoolean networks (BNs) provide an effective modelling formalism for various complex biochemical phenomena. Their long term behaviour is represented by attractors-subsets of the state space towards which the BN eventually converges. These are then typically linked to different biological phenotypes. Depending on various logical parameters, the structure and quality of attractors can undergo a significant change, known as a bifurcation. We present a methodology for analysing bifurcations in asynchronous parametrised Boolean networks.ResultsIn this paper, we propose a computational framework employing advanced symbolic graph algorithms that enable the analysis of large networks with hundreds of Boolean variables. To visualise the results of this analysis, we developed a novel interactive presentation technique based on decision trees, allowing us to quickly uncover parameters crucial to the changes in the attractor landscape. As a whole, the methodology is implemented in our tool AEON. We evaluate the method's applicability on a complex human cell signalling network describing the activity of type-1 interferons and related molecules interacting with SARS-COV-2 virion. In particular, the analysis focuses on explaining the potential suppressive role of the recently proposed drug molecule GRL0617 on replication of the virus.ConclusionsThe proposed method creates a working analogy to the concept of bifurcation analysis widely used in kinetic modelling to reveal the impact of parameters on the system's stability. The important feature of our tool is its unique capability to work fast with large-scale networks with a relatively large extent of unknown information. The results obtained in the case study are in agreement with the recent biological findings.

| S-EPMC9092939 | biostudies-literature

Associative Learning by Classical Conditioning in Liquid Crystal Network Actuators.

Project description:Responsive and shape-memory materials allow stimuli-driven switching between fixed states. However, their behavior remains unchanged under repeated stimuli exposure, i.e., their properties do not evolve. By contrast, biological materials allow learning in response to past experiences. Classical conditioning is an elementary form of associative learning, which inspires us to explore simplified routes even for inanimate materials to respond to new, initially neutral stimuli. Here, we demonstrate that soft actuators composed of thermoresponsive liquid crystal networks "learn" to respond to light upon a conditioning process where light is associated with heating. We apply the concept to soft microrobotics, demonstrating a locomotive system that "learns to walk" under periodic light stimulus, and gripping devices able to "recognize" irradiation colors. We anticipate that actuators that algorithmically emulate elementary aspects of associative learning and whose sensitivity to new stimuli can be conditioned depending on past experiences may provide new routes toward adaptive, autonomous soft microrobotics.

| S-EPMC6961496 | biostudies-literature

Attractor-map versus autoassociation based attractor dynamics in the hippocampal network.

Project description:The autoassociative memory model of hippocampal field CA3 postulates that Hebbian associations among external input features produce attractor states embedded in a recurrent synaptic matrix. In contrast, the attractor-map model postulates that a two-dimensional continuum of attractor states is preconfigured in the network during development and that transitions among these states are governed primarily by self-motion information ("path-integration"), giving rise to the strong spatial characteristic of hippocampal activity. In this model, learned associations between "coordinates" on the attractor map and external cues can result in abrupt jumps between states, in the case of mismatches between the current input and previous associations between internal coordinates and external landmarks. Both models predict attractor dynamics, but for fundamentally different reasons; however, the two models are not a priori mutually exclusive. We contrasted these two models by comparing the dynamics of state transitions when two previously learned environmental shapes were morphed between their endpoints, in animals that had first experienced the environments either at the same location, or at two different locations, connected by a passageway through which they walked. As predicted from attractor-map theory, the latter animals expressed abrupt transitions between representations at the midpoint of the morph series. Contrary to the predictions of autoassociation theory, the former group expressed no evidence of attractor dynamics during the morph series; there was only a gradual transition between endpoints. The results of this critical test thus cast the autoassociator theory for CA3 into doubt and indicate the need for a new theory for this structure.

| S-EPMC2904215 | biostudies-literature

Lifelong Machine Learning Potentials.

Project description:Machine learning potentials (MLPs) trained on accurate quantum chemical data can retain the high accuracy, while inflicting little computational demands. On the downside, they need to be trained for each individual system. In recent years, a vast number of MLPs have been trained from scratch because learning additional data typically requires retraining on all data to not forget previously acquired knowledge. Additionally, most common structural descriptors of MLPs cannot represent efficiently a large number of different chemical elements. In this work, we tackle these problems by introducing element-embracing atom-centered symmetry functions (eeACSFs), which combine structural properties and element information from the periodic table. These eeACSFs are key for our development of a lifelong machine learning potential (lMLP). Uncertainty quantification can be exploited to transgress a fixed, pretrained MLP to arrive at a continuously adapting lMLP, because a predefined level of accuracy can be ensured. To extend the applicability of an lMLP to new systems, we apply continual learning strategies to enable autonomous and on-the-fly training on a continuous stream of new data. For the training of deep neural networks, we propose the continual resilient (CoRe) optimizer and incremental learning strategies relying on rehearsal of data, regularization of parameters, and the architecture of the model.

| S-EPMC10308836 | biostudies-literature

Associative fear learning enhances sparse network coding in primary sensory cortex.

Project description:Several models of associative learning predict that stimulus processing changes during association formation. How associative learning reconfigures neural circuits in primary sensory cortex to "learn" associative attributes of a stimulus remains unknown. Using 2-photon in vivo calcium imaging to measure responses of networks of neurons in primary somatosensory cortex, we discovered that associative fear learning, in which whisker stimulation is paired with foot shock, enhances sparse population coding and robustness of the conditional stimulus, yet decreases total network activity. Fewer cortical neurons responded to stimulation of the trained whisker than in controls, yet their response strength was enhanced. These responses were not observed in mice exposed to a nonassociative learning procedure. Our results define how the cortical representation of a sensory stimulus is shaped by associative fear learning. These changes are proposed to enhance efficient sensory processing after associative learning.

| S-EPMC3398404 | biostudies-literature

Deep Bayesian Unsupervised Lifelong Learning.

Project description:Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much attention has been given lately to Supervised Lifelong Learning (SLL) with a stream of labelled data. In contrast, we focus on resolving challenges in Unsupervised Lifelong Learning (ULL) with streaming unlabelled data when the data distribution and the unknown class labels evolve over time. Bayesian framework is natural to incorporate past knowledge and sequentially update the belief with new data. We develop a fully Bayesian inference framework for ULL with a novel end-to-end Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, which can progressively discover new clusters without forgetting the past with unlabelled data while learning latent representations. To efficiently maintain past knowledge, we develop a novel knowledge preservation mechanism via sufficient statistics of the latent representation for raw data. To detect the potential new clusters on the fly, we develop an automatic cluster discovery and redundancy removal strategy in our inference inspired by Nonparametric Bayesian statistics techniques. We demonstrate the effectiveness of our approach using image and text corpora benchmark datasets in both LL and batch settings.

| S-EPMC8969892 | biostudies-literature

A pilot study exploring the relationship between lifelong learning and factors associated with evidence-based medicine.

Project description:ObjectivesTo explore possible relationships between residents' lifelong learning orientation, skills in practicing evidence-based medicine (EBM), and perceptions of the environment for learning and practicing EBM.MethodsThis was a pilot study with a cross-sectional survey design. Out of 60 residents in a medical residency program, 29 participated in the study. Data were collected using a survey that comprised three sections: the JeffSPLL Scale, EBM Environment Scale, and an EBM skill questionnaire. Data were analyzed using SPSS and were reported with descriptive and inferential statistics (mean, standard deviation, Pearson's correlation, and a two-sample t-test).ResultsMean scores on the JeffSPLL Scale were significantly correlated with perceptions of the EBM Scale and use of EBM resources to keep up to date or solve a specific patient care problem. There was a significant correlation between mean scores on the EBM Scale and hours per week spent in reading medical literature to solve a patient care problem. Two-sample t-tests show that residents with previous training in research methods had significantly higher scores on the JeffSPLL Scale (p=0.04), EBM Scale (p=0.006), and self-efficacy scale (p =0.024).ConclusionsGiven the fact that physicians are expected to be lifelong learners over the course of their professional career, developing residents' EBM skills and creating interventions to improve specific areas in the EBM environment would likely foster residents' lifelong learning orientation.

| S-EPMC4939218 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data