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
From an E-narrative Poem towards an Interactive Work of Art. Media Convergence Illustrated with DOWN by Zenon Fajfer and The Surprising Spiral by Ken Feingold
[chapter]
2015
On-line/Off-line. Between Text and Experience Writing as a Lifestyle
Preserved Fulltext
changeable, iconic, set in a computer program, double-indirect), paying attention to the meaningfulness of the disciplines borderland (in this case literary and media studies) The author stresses the reasonableness ...
of the question asked by Katarzyna Bazarnik, whether, by accident, the "Darwinian" evolution of species continues In the author's opinion, based on her observation of works belonging to the literary style ...
A different book structure is tantamount to a different physics. The invisible text is meta-physics Somewhere in between there is the reader who learns to read anew. (Fajfer 2010: 107-109) . ...
doi:10.18778/7969-821-9.20
fatcat:74quq57ksjgwhpeno2a67oevu4
Adaptive fuzzy command acquisition with reinforcement learning
1998
IEEE transactions on fuzzy 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 2017; you can also visit the original URL.
The file type is application/pdf.
The AFCAN can perform off-line as well as on-line learning. ...
The AFCAN can also perform on-line learning interactively when it is in use for fuzzy command acquisition. ...
ACKNOWLEDGMENT The authors would like to thank the reviewers for their helpful suggestions in improving the quality of the final manuscript. ...
doi:10.1109/91.660811
fatcat:3oukx4d2pjbh5lku2phox5dokq
Getting to Know Your Neighbors: Unsupervised Learning of Topography from Real-World, Event-Based Input
2009
Neural Computation
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 algorithm was tested on real data from a 64 × 64-pixel section of an event-based temporal contrast silicon retina and a 360-tile tactile luminous floor. ...
The algorithm was tested on real data from a 64 × 64-pixel section of an event-based temporal contrast silicon retina and a 360-tile tactile luminous floor. ...
In addition, we thank the developers of the tactile sensory floor: Rodney Douglas, Adrian Whatley, Paul Verschure, Klaus Hepp, and the rest of the Ada exhibit team. ...
doi:10.1162/neco.2009.06-07-554
pmid:19431283
fatcat:cgls3u6vnzggjpvwhfvuzfw22e
Practical Issues in Temporal Difference Learning
[chapter]
1992
Reinforcement Learning
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 2012; you can also visit the original URL.
The file type is application/pdf.
This paper examines whether temporal difference methods for training connectionist networks, such as Sutton's TD(X) algorithm, can be successfully applied to complex real-world problems. ...
This indicates that TD learning may work better in practice than one would expect based on current theory, and it suggests that further analysis of TD methods, as well as applications in other complex ...
Acknowledgments The author thanks Scott Kirkpatrick and Rich Sutton for helpful comments on an earlier version of the manuscript. ...
doi:10.1007/978-1-4615-3618-5_3
fatcat:apwipljwznegrehyvw2uvxkziq
Practical issues in temporal difference learning
1992
Machine Learning
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 2012; you can also visit the original URL.
The file type is application/pdf.
This paper examines whether temporal difference methods for training connectionist networks, such as Sutton's TD(X) algorithm, can be successfully applied to complex real-world problems. ...
This indicates that TD learning may work better in practice than one would expect based on current theory, and it suggests that further analysis of TD methods, as well as applications in other complex ...
Acknowledgments The author thanks Scott Kirkpatrick and Rich Sutton for helpful comments on an earlier version of the manuscript. ...
doi:10.1007/bf00992697
fatcat:f3hirqeamnh4vaoygwomxl55si
:{unav)
2012
Machine Learning
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 paper examines whether temporal difference methods for training connectionist networks, such as Sutton's TD(X) algorithm, can be successfully applied to complex real-world problems. ...
This indicates that TD learning may work better in practice than one would expect based on current theory, and it suggests that further analysis of TD methods, as well as applications in other complex ...
Acknowledgments The author thanks Scott Kirkpatrick and Rich Sutton for helpful comments on an earlier version of the manuscript. ...
doi:10.1023/a:1022624705476
fatcat:yc62x7u65zfcnag6qcyww2et2y
A spatio-temporal probabilistic model for multi-sensor object recognition
2007
2007 IEEE/RSJ International Conference on Intelligent Robots and 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 2015; you can also visit the original URL.
The file type is application/pdf.
We demonstrate the benefits of modelling spatial and temporal relationships for the problem of detecting cars using laser and vision data in outdoor environments. ...
The algorithm is developed in the context of Conditional Random Fields (CRFs) trained with virtual evidence boosting. ...
Corresponding to different variants of temporal state estimation, our spatio-temporal model can be deployed to perform three different types of estimation. • Off-line smoothing: All scans in a temporal ...
doi:10.1109/iros.2007.4399537
dblp:conf/iros/DouillardFR07
fatcat:ecuuws6hpvhilkfmnic77yzlpm
The Effects of Theta Precession on Spatial Learning and Simplicial Complex Dynamics in a Topological Model of the Hippocampal Spatial Map
2014
PLoS Computational Biology
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
To make the model more physiological, we explored the effects of theta precession on spatial learning in our virtual ensembles. ...
We previously showed that ensembles of hundreds of place cells could accurately encode topological information about different environments ("learn" the space) within certain values of place cell firing ...
Designed the software used in analysis: MA YD. ...
doi:10.1371/journal.pcbi.1003651
pmid:24945927
pmcid:PMC4063672
fatcat:d64s7na6uvgpdkcidaa6ol4mgm
Prioritized Sweeping Neural DynaQ with Multiple Predecessors, and Hippocampal Replays
[chapter]
2018
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 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The Dyna reinforcement learning algorithms use off-line replays to improve learning. ...
These have been interpreted as a memory consolidation process, but recent results suggest a possible interpretation in terms of reinforcement learning. ...
Results
Learning the world model Because of correlations in sample sequences, the world model is learned off-line: the samples are presented in random order, so as to break temporal correlations. ...
doi:10.1007/978-3-319-95972-6_4
fatcat:abjqy35lmzdgraxd6mxwul35eq
Context-Aware Online Spatiotemporal Traffic Prediction
2014
2014 IEEE International Conference on Data Mining Workshop
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 2015; you can also visit the original URL.
The file type is application/pdf.
In particular, the proposed framework uses a set of base predictors (e.g. a Support Vector Machine or a Bayes classifier) and learns in real-time the most effective one to use in different contexts (e.g ...
One key challenge in predicting traffic congestion is how much to rely on the historical data v.s. the real-time data. ...
Ensuring a fast convergence rate is important for the algorithm to quickly adapt to the dynamically changing environment.
IV. EXPERIMENTS A. ...
doi:10.1109/icdmw.2014.102
dblp:conf/icdm/XuDDSS14
fatcat:65queqbucbf4bj4galkwogpigu
A Spatio-Temporal Probabilistic Model for Multi-Sensor Multi-Class Object Recognition
[chapter]
2010
Springer Tracts in Advanced Robotics
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 2008; you can also visit the original URL.
The file type is application/pdf.
We demonstrate the benefits of modelling spatial and temporal relationships for the problem of detecting seven classes of objects using laser and vision data in outdoor environments. ...
This paper presents a general probabilistic framework for multisensor multi-class object recognition based on Conditional Random Fields (CRFs) trained with virtual evidence boosting. ...
Corresponding to different variants of temporal state estimation, our spatio-temporal model can be deployed to perform three different types of estimation. • Off-line smoothing: All scans in a temporal ...
doi:10.1007/978-3-642-14743-2_11
fatcat:qnz6s6c6pngt7khmivmlyujsia
Isotropic Sequence Order Learning
2003
Neural Computation
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 2006; you can also visit the original URL.
The file type is application/pdf.
Finally we discuss the relation of ISO-learning with other drive reinforcement models and with the commonly used "temporal difference" (TD-) learning algorithm. ...
We investigate the algorithm in an open-and a closed-loop condition, the latter being defined by embedding the learning system into a behavioural feedback loop. ...
Acknowledgements We are grateful to Christian von Ferber, Leslie Smith, Richard Reeve and in general to the members of the CCCN-seminar for their helpful comments during various stages of this work. ...
doi:10.1162/08997660360581921
pmid:12689389
fatcat:zjr5cbs3rjh7hn26bwijbbnzre
Learning Sensor Data Characteristics in Unknown Environments
2006
2006 Third Annual International Conference on Mobile and Ubiquitous Systems: Networking & Services
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 2007; you can also visit the original URL.
The file type is application/pdf.
In this paper, we motivate and propose an online algorithm that leverages a Competitive Learning Neural Network (CLNN) for characterization of a dynamic, unknown environment. ...
Based on the proposed characterization sensor networks can autonomously construct multimodal views of their environments and derive the conditions for verifying data integrity over time. ...
Dynamics: Time Varying Shadows This experiment studies whether the proposed algorithm is robust and can adapt to dynamics of the environment and in the presence of a temporal noise in the sensor readings ...
doi:10.1109/mobiq.2006.340384
dblp:conf/mobiquitous/BokarevaBJ06
fatcat:hqng3xuvqfddbphz36n5n6flmq
Reinforcement Learning: Insights from Interesting Failures in Parameter Selection
[chapter]
2008
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 2016; you can also visit the original URL.
The file type is application/pdf.
We investigate reinforcement learning methods, namely the temporal difference learning TD(λ) algorithm, on game-learning tasks. ...
Small modifications in algorithm setup and parameter choice can have significant impact on success or failure to learn. ...
Sutton's well-known temporal difference (TD) learning algorithm is a specific method to deal with the credit assignment problem in control and decision tasks [1] . ...
doi:10.1007/978-3-540-87700-4_48
fatcat:sgyr4ifhvjfcbbg7rboy5ahfjy
Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence
[article]
2018
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.
in a simulated environment. ...
On the algorithmic front, we propose a simple and natural sequential multi-point BCO algorithm amenable to wireless networking optimisation, and provide its theoretical analysis. ...
In order to have a clearer picture of the oscillatory effects, we plot now the temporal evolution ofT off for a single simulation run in Fig. 2 , for different values of ω and exploration schedules h( ...
arXiv:1802.04327v1
fatcat:vt2szfnxezd3tgxsahh34gvhse
« Previous
Showing results 1 — 15 out of 19,944 results