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
Minimalistic Unsupervised Learning with the Sparse Manifold Transform
[article]
2022
arXiv
pre-print
Preserved Fulltext
Our approach leverages the sparse manifold transform, which unifies sparse coding, manifold learning, and slow feature analysis. ...
With a one-layer deterministic sparse manifold transform, one can achieve 99.3% KNN top-1 accuracy on MNIST, 81.1% KNN top-1 accuracy on CIFAR-10 and 53.2% on CIFAR-100. ...
This process is called the sparse manifold transform [20] .
UNSUPERVISED LEARNING WITH THE SPARSE MANIFOLD TRANSFORM The sparse manifold transform. ...
arXiv:2209.15261v1
fatcat:unqysidbqzetppfz74hflmtimy
Predictive Sparse Manifold Transform
[article]
2023
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 2024; you can also visit the original URL.
The file type is application/pdf.
We present Predictive Sparse Manifold Transform (PSMT), a minimalistic, interpretable and biologically plausible framework for learning and predicting natural dynamics. ...
PSMT incorporates two layers where the first sparse coding layer represents the input sequence as sparse coefficients over an overcomplete dictionary and the second manifold learning layer learns a geometric ...
Conclusion We present Predictive Sparse Manifold Transform (PSMT), a two-layer unsupervised generative model to learn and predict natural dynamics. ...
arXiv:2308.14207v1
fatcat:fif5azqjejdafjlcjufjesdmya
An Evaluation of Supervised Dimensionality Reduction For Large Scale Data
2022
Journal of Machine and Computing
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.
Experimenters today frequently quantify millions or even billions of characteristics (measurements) each sample to address critical biological issues, in the hopes that machine learning tools would be ...
present in the person's body). ...
CONCLUSION An important aspect of unsupervised manifold learning may be transformed into supervised manifold learning by adding class-conditional moment estimations. ...
doi:10.53759/7669/jmc202202003
fatcat:5uygro7p4rbb7cfhgr7nvdkp4m
Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive ...
This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically ...
, manifold learning, and density estimation. ...
arXiv:2001.00378v2
fatcat:ysvljxylwnajrbowd3kfc7l6ve
You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval
[article]
2024
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 2024; you can also visit the original URL.
The file type is application/pdf.
Other Versions
a duet between the two. ...
In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating ...
L TT is multi-fold -(i) it alleviates seen set overfitting, (ii) typically, learned prompts reside in the sparse regions of the CLIP manifold [2] , limiting its intractability with actual query texts ...
arXiv:2403.07222v2
fatcat:6qhd6sepsvgkvfsishqtrg3pju
Emergence of Segmentation with Minimalistic White-Box Transformers
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
in the data distribution, segmentation properties, at both the whole and parts levels, already emerge with a minimalistic supervised training recipe. ...
In this study, we probe whether segmentation emerges in transformer-based models solely as a result of intricate self-supervised learning mechanisms, or if the same emergence can be achieved under much ...
We thank Xudong Wang and Baifeng Shi for valuable discussions on segmentation properties in vision transformers. ...
arXiv:2308.16271v1
fatcat:awdwz43o65bwzjds7t4zayyzme
On the role of nonlinear correlations in reduced-order modelling
2022
Journal of Fluid Mechanics
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.
In the latter case, we use sparse polynomial regression to learn a compact, interpretable dynamical system model from the time series of the active modal coefficients. ...
of driving modes and a manifold equation for the remaining modes. ...
Nonlinear correlations in reduced-order modelling Predictive mean-flow analysis is the subject of ongoing work, for example with eddy viscosity-based Reynolds-averaged Navier-Stokes mean-flow estimates ...
doi:10.1017/jfm.2021.994
fatcat:7m4prm3vkjcfvia34o3fy6bhp4
A Review of Generalizable Transfer Learning in Automatic Emotion Recognition
2020
Frontiers 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 2020; you can also visit the original URL.
The file type is application/pdf.
An effective way to address challenges related to the scarcity of data and lack of human labels, is transfer learning. ...
In this manuscript, we will describe fundamental concepts in the field of transfer learning and review work which has successfully applied transfer learning for automatic emotion recognition. ...
This research was funded by the Engineering Information Foundation (EiF18.02) and the Texas A&M Program to Enhance Scholarly and Creative Activities (PESCA). ...
doi:10.3389/fcomp.2020.00009
fatcat:o3ya5n2nvjbptnxkqahpgrluie
Neural Simpletrons - Minimalistic Directed Generative Networks for Learning with Few Labels
[article]
2016
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 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Empirical evaluations on standard benchmarks show, that for datasets with few labels the derived minimalistic network improves on all classical deep learning approaches and is competitive with their recent ...
With the single objective of likelihood optimization, both labeled and unlabeled data are naturally incorporated into learning. ...
interplay between supervised and unsupervised learning. ...
arXiv:1506.08448v4
fatcat:gswa3d4fifgaxfr63nfux2a4ze
Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community
2017
Journal of Applied Remote Sensing
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.
Other Versions
machine learning, to name a few. ...
In recent years, deep learning (DL), a re-branding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, natural language processing, etc. ...
Acknowledgments The authors wish to thank graduate students Vivi Wei, Julie White, and Charlie Veal for their valuable inputs related to DL tools. ...
doi:10.1117/1.jrs.11.042609
fatcat:tdbssxma3fettcjy5iqgo6afwa
Design of software-oriented technician for vehicle's fault system prediction using AdaBoost and random forest classifiers
2022
International Journal of Engineering, Science and Technology
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.
The scope of this system is to visualize the data acquired from vehicle, diagnosis the fault component using trained fault model obtained from improvised Machine Learning (ML) classifiers and generate ...
The visualization page is built with plotly python package and prepared with selected parameter from On-board Diagnosis (OBD) tool data. ...
Unsupervised Machine Learning Algorithms Unsupervised learning is learning that does not include the direct control of the user. ...
doi:10.4314/ijest.v14i1.4
fatcat:ib4ecaua7re75hxtrhvxgaigqi
On Organizational Principles of Neural Systems
[article]
2024
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 2024; you can also visit the original URL.
The file type is application/pdf.
We hope this survey article can inspire new research at the intersection of neuroscience and learning systems, helping bridge the gap between natural and artificial intelligence. ...
At each level, we use mathematical models as our abstractions and study their organizational principles (e.g., entropy reduction, predictive coding, and coordinate transformation). ...
Proposition 2 (Principle of Manifold Untangling): The task of sensorimotor learning via coordinate transformations can be facilitated by simultaneously untangling the neural manifold of sensory and motor ...
arXiv:2402.14186v1
fatcat:uztev5xjpvavjkat4g3xn7hdzi
Table of Contents
2022
IEEE Robotics and Automation Letters
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.
Seo 2-Dimensional Dynamic Analysis of Inverted Pendulum Robot With Transformable Wheel for Overcoming Steps. . . . . . ...
Tang Visual Localization and Mapping Leveraging the Constraints of Local Ground Manifolds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ...
doi:10.1109/lra.2022.3165102
fatcat:enjzebowe5hn7hsfwklc7nieuy
The Autodidactic Universe
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
These protocols together provide a number of directions in which to explore the origin of physical laws based on putting machine learning architectures in correspondence with physical theories. ...
We propose that if the neural network model can be said to learn without supervision, the same can be said for the corresponding physical theory. ...
• There is also an inverse transformation from matrices to gauge fields on compact manifolds, described in [10] . ...
arXiv:2104.03902v2
fatcat:zlq7swbxa5b6xhoruxai6xr5du
Natural Image Coding in V1: How Much Use Is Orientation Selectivity?
2009
PLoS Computational Biology
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.
Other Versions
the average log-loss we compute, for the first time, complete rate-distortion curves for ICA in comparison with PCA. ...
The most parsimonious one among these models is linear Independent Component Analysis (ICA), whereas second-order decorrelation transformations such as Principal Component Analysis (PCA) do not yield oriented ...
Acknowledgments We would like to thank Philipp Berens, Roland Fleming, Jakob Macke and Bruno Olshausen for fruitful discussions and helpful comments on the manuscript.
Author Contributions ...
doi:10.1371/journal.pcbi.1000336
pmid:19343216
pmcid:PMC2658886
fatcat:kri3giuo3vb7dgy6lbwqbcbb4i
« Previous
Showing results 1 — 15 out of 89 results