A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Brain-like combination of feedforward and recurrent network components achieves prototype extraction and robust pattern recognition
[article]
2022
arXiv
pre-print
Preserved Fulltext
Other Versions
We approach this problem by combining a recurrent attractor network with a feedforward network that learns distributed representations using an unsupervised Hebbian-Bayesian learning rule. ...
The associative memory is also shown to perform prototype extraction from the training data and make the representations robust to severely distorted input. ...
learning algorithms. ...
arXiv:2206.15036v2
fatcat:ugjorhvldvc7rnmjkvbrv2bgpm
Using Machine Learning to Improve Personalised Prediction: A Data-Driven Approach to Segment and Stratify Populations for Healthcare
[chapter]
2022
Studies in Health Technology and Informatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This study combines unsupervised clustering for segmentation and supervised classification, personalised to clusters, for stratification. ...
Cluster a priori or Unsupervised Classify PARR-30 or GLMM Predict Optimise Risk Cutoff Figure 1 . Flowchart of methods used to cluster-then-predict using both supervised and unsupervised learning. ...
would result in improved predictions, unsupervised clustering was undertaken using k-prototypes in order for both binary and continuous variables to be used [14] . ...
doi:10.3233/shti210851
pmid:35062084
fatcat:5umuj2ek4bax5j5bequmhi5xsm
Learning in Computer Vision and Image Understanding
1993
Neural Information Processing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Methods to combine unsupervised and supervised data clustering with elastic matching to learn a discriminant metric and enhance saliency of prototypes were discussed. ...
Eric Saund of Xerox introduced the window registration problem in unsupervised learning of visual features. ...
dblp:conf/nips/Greenspan93
fatcat:qrnzgx267vbhvg62em24zo3om4
Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly
2021
Neural Information Processing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
A current remarkable improvement of unsupervised visual representation learning is based on heavy networks with large-batch training. ...
We also introduce a network driven multi-view generation paradigm to capture rich feature information contained in the network itself. ...
Introduction Recently, there has been a growing attention in unsupervised and self-supervised learning where the goal is to effectively learn useful features from a large amount of unlabeled data. ...
dblp:conf/nips/ChoiKO21
fatcat:6jqp3jlwcjgupekiwfbzyzkogq
Prototyping Machine Learning Through Diffractive Art Practice
2021
Designing Interactive Systems Conference 2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
tools, with the hope of revealing the computational materiality of ML, and the potential of embodiment to craft prototypes of ML that reconfigure conceptual or technical approaches to ML. ...
We derive five interference conditions for such art-based ML prototypes-situational whole, small data, shallow model, learnable algorithm, and somaesthetic behaviourand describe their widening of design ...
their precious time and feedback experimenting with them. ...
doi:10.1145/3461778.3462163
fatcat:aorswggm5fa6pkdttpbt3m76ku
Self-Supervised Visual Representation Learning with Semantic Grouping
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Instead, we propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning. ...
Based on the learned data-dependent slots, a contrastive objective is employed for representation learning, which enhances the discriminability of features, and conversely facilitates grouping semantically ...
We propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning. ...
arXiv:2205.15288v2
fatcat:dafyhiaxijcn3mok4fbv6is6zm
Text Mining in Qualitative Research
2008
Organizational Research Methods
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The SOM is a versatile quantitative method very commonly used across many disciplines to analyze large data sets. ...
SOM creates multiple well-grounded perspectives on the data and thus improves the quality of the concepts and categories used in the analysis. ...
Thus, unsupervised learning may give rise to novel model constructions autonomously emerging from the data. ...
doi:10.1177/1094428108317202
fatcat:puub5w3luzgjbaja2hv3l2nbfa
Biometric Encryption: Integrating Artificial Intelligence for Robust Authentication
2023
Dandao xuebao
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
approach, aiming not only to overcome these challenges but also to adapt and evolve in response to emerging threats. ...
This research paper delves into the intricate integration of Artificial Intelligence (AI) with biometric encryption systems to elevate authentication robustness to unprecedented levels. ...
Dandao
3.1.2Unsupervised Learning: Unsupervised learning is applied when labeled training data is scarce. ...
doi:10.52783/dxjb.v35.121
fatcat:covke5rahffo5fqk6as75lgcdu
Learning Representations for Animated Motion Sequence and Implied Motion Recognition
[chapter]
2012
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The paper develops a cortical model architecture for the unsupervised learning of animated motion sequence representations. ...
We also show how sequence selective representations are learned in STS by fusing snapshot and motion input and how learned feedback connections enable making predictions about future input. ...
Feedback between stabilizes the feature processing from raw input. Representations of prototypical form and motion responses are established by utilizing unsupervised Hebbian learning. ...
doi:10.1007/978-3-642-33269-2_37
fatcat:poflinvf75fnbii2vnqwn6ccka
Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions
2016
Frontiers in Computational Neuroscience
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account ...
(C) Different types of high-level features (receptive fields) emerging from unsupervised deep learning. ...
For example, in the domain of visual object recognition, unsupervised deep learning can lead to the emergence of extremely high-level visual features (Figure 2C) , such as those representing prototypical ...
doi:10.3389/fncom.2016.00073
pmid:27468262
pmcid:PMC4943066
fatcat:vlybqbpt4re5dmbc2fsg5c2opu
Environment and Goals Jointly Direct Category Acquisition
2005
Current Directions in Psychological Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Existing models of category learning, such as exemplar and prototype models, neglect the role of goals in shaping conceptual organization. ...
Clusters reflect the natural bundles of correlated features present in our environment. ...
Recent work in collaboration with Yasuaki Sakamoto has demonstrated that inference learning leads to more complete knowledge of feature correlations than does classification learning, even for features ...
doi:10.1111/j.0963-7214.2005.00363.x
fatcat:ajuy2du6jnbwxeubzc64swu5vi
Modeling language and cognition with deep unsupervised learning: a tutorial overview
2013
Frontiers in Psychology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This approach does not require labeled data (i.e., learning is unsupervised). ...
Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. ...
Accordingly, for each pattern the network performs a data-driven, positive phase (+) and a model-driven, negative phase (-). ...
doi:10.3389/fpsyg.2013.00515
pmid:23970869
pmcid:PMC3747356
fatcat:hnszejz7yfeufgsdfbuxktplbe
Memory Organization for Invariant Object Recognition and Categorization
2016
ELCVIA Electronic Letters on Computer Vision and Image Analysis
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The overall results indicate that medium-sized image features with ...
These patches are represented by regular-shaped graphs, whose nodes are labeled with elementary features that capture texture information from the object view. ...
The present work also studies alternatives employing emergent structures from the unsupervised clustering of the feature distribution using the Enhanced Tree Growing Neural Gas [13] . ...
doi:10.5565/rev/elcvia.954
fatcat:pzi7ynxognfurinhelumk5ayve
The Impact of AI and Machine Learning on Innovation: A Comprehensive Review
2023
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Artificial Intelligence (AI) and Machine Learning (ML) have emerged as transformative technologies with the potential to revolutionize various industries and spur innovation. ...
Unsupervised Learning: Unsupervised learning involves training models on unlabeled data to discover patterns or structures within the data. ...
Integration of AI and ML with Emerging Technologies: The integration of AI and ML with other emerging technologies will shape the future of innovation. ...
doi:10.5281/zenodo.10071190
fatcat:rxpli5dtm5b43cj3xylcvp2yry
An NWDAF Approach to 5G Core Network Signaling Traffic: Analysis and Characterization
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The work presented in this paper focuses on demonstrating a working system prototype of the 5G Core (5GC) network and the Network Data Analytics Function (NWDAF) used to bring the benefits of data-driven ...
Analyses of the network-generated data explore core intra-network interactions through unsupervised learning, clustering, and evaluate these results as insights for future opportunities and works. ...
This was accomplished by leveraging unsupervised learning, and the k-Means clustering algorithm with a variable number of clusters set a priori. ...
arXiv:2209.10428v3
fatcat:2ieoe7t6lvaapl53xaks6ctbqe
« Previous
Showing results 1 — 15 out of 7,248 results