Filters








37,384 Hits in 6.3 sec

An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration

Yumin Su, Liang Zhang, Quanyu Dai, Bo Zhang, Jinyao Yan, Dan Wang, Yongjun Bao, Sulong Xu, Yang He, Weipeng Yan
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
Conversion rate (CVR) prediction is becoming increasingly important in the multi-billion dollar online display advertising industry.  ...  Existing models usually suffer from such scarce and delayed conversion behaviors. In this paper, we propose a novel deep learning framework to tackle the two challenges.  ...  Considering the above, we propose that designing a P EM is, without loss of generality, a regression task, where the goal is to learn the rules and parameters which describe the difference (E) between  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/483">doi:10.24963/ijcai.2020/483</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/PiazzoniCSD20.html">dblp:conf/ijcai/PiazzoniCSD20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5fwdjw23qjeyfgcdeju6upd6km">fatcat:5fwdjw23qjeyfgcdeju6upd6km</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104181405/https://www.ijcai.org/Proceedings/2020/0483.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4d/21/4d2193b75a3c742d3f14c78a7c034cd8b434c609.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/483"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback [article]

Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He
<span title="2021-08-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although the prophet cannot be obtained during online learning, we show that we could predict the prophet's predictions by an aggregation policy on top of a set of multi-task predictions, where each task  ...  The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days  ...  Multi-task learning for delayed feedback Recall that, without considering the delayed feedback, we can use the standard binary cross-entropy objective function to optimize a single CVR prediction model  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.06167v1">arXiv:2108.06167v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hc4hdnht3jdiffgq3otsg3w4ru">fatcat:hc4hdnht3jdiffgq3otsg3w4ru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210820062553/https://arxiv.org/pdf/2108.06167v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2d/1b/2d1b848696e12907a453ec0e60b0588495bb29a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.06167v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction [article]

Yu Chen, Jiaqi Jin, Hui Zhao, Pengjie Wang, Guojun Liu, Jian Xu, Bo Zheng
<span title="2022-02-15">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Alleviating the delayed feedback problem is of crucial importance for the conversion rate(CVR) prediction in online advertising.  ...  delay conversions.  ...  RELATED WORK 2.1 Delayed Feedback Models Learning with delayed feedback has received considerable attention in the studies of predicting conversion rate (CVR).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.06472v2">arXiv:2202.06472v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ki3p4uno6zh27hdjln2qymyidu">fatcat:ki3p4uno6zh27hdjln2qymyidu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220515093518/https://arxiv.org/pdf/2202.06472v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/43/47/4347a41d63b224f1530d29ae702213fb87a5b3c3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.06472v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems [article]

Jia-Qi Yang, De-Chuan Zhan
<span title="2022-06-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Predicting conversion rate (e.g., the probability that a user will purchase an item) is a fundamental problem in machine learning based recommender systems.  ...  Previous literature concentrates on utilizing early conversions to mitigate such a delayed feedback problem.  ...  However, learning with delayed feedback is different from general multi-task learning problems without delayed feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00407v1">arXiv:2206.00407v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zt7zpctmnndgrc7msgqfp5q4sq">fatcat:zt7zpctmnndgrc7msgqfp5q4sq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220605165929/https://arxiv.org/pdf/2206.00407v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/48/c2/48c2a12c72d6cc7661aebbaa15b18fd8a6b3f8ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00407v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling [article]

Siyu Gu, Xiang-Rong Sheng, Ying Fan, Guorui Zhou, Xiaoqiang Zhu
<span title="2021-08-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
One of the difficulties of conversion rate (CVR) prediction is that the conversions can delay and take place long after the clicks.  ...  These issues induce bias during the modeling of delayed feedback. In this paper, we propose DElayed FEedback modeling with Real negatives (DEFER) method to address these issues.  ...  Online Serving with Offline Training. We evaluate the proposed multi-task approach on a scenario of our display advertising system that uses offline training.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.14121v2">arXiv:2104.14121v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xfyg6jl6zjd7zklzfnhvaaqlx4">fatcat:xfyg6jl6zjd7zklzfnhvaaqlx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210819105959/https://arxiv.org/pdf/2104.14121v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/e7/59e76a7cac4a79a6c0dc1f609a116d1ebdc894c9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.14121v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction [article]

Yanshi Wang, Jie Zhang, Qing Da, Anxiang Zeng
<span title="2020-11-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
CVR models are trained with clicked impressions while making inference on the entire space of all impressions; iii) delayed feedback: many conversions can only be observed after a relatively long and  ...  However, CVR prediction usually suffers from three major challenges in practice: i) data sparsity: compared with impressions, conversion samples are often extremely scarce; ii) sample selection bias: conventional  ...  Conclusions In this paper, we propose a novel neural network framework to unitedly tackle data sparsity, sample selection bias and feedback delay challenges in CVR prediction.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.11826v1">arXiv:2011.11826v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xnhnfe465fgxbkq37hdfbgzcg4">fatcat:xnhnfe465fgxbkq37hdfbgzcg4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201128230301/https://arxiv.org/pdf/2011.11826v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/40/ec404e72fbd3e636f8f71a6b7a79a538a1f527f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.11826v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed [article]

Giovanni Sutanto, Katharina Rombach, Yevgen Chebotar, Zhe Su, Stefan Schaal, Gaurav S. Sukhatme, Franziska Meier
<span title="2020-06-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We evaluate our approach on a real anthropomorphic robot in learning a tactile feedback task.  ...  In the final phase, a sample-efficient reinforcement learning algorithm fine-tunes these feedback models for novel task settings through few real system interactions.  ...  Learning a local feedback model is more sample-efficient as compared to learning a global predictive model for a replanning approach, and hence we choose to work on the former in this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.00450v1">arXiv:2007.00450v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/chzm5eduvbe2padut4kedgvfsy">fatcat:chzm5eduvbe2padut4kedgvfsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710050112/https://arxiv.org/pdf/2007.00450v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/02/5f/025f3f076aa9fa1c5d7694bdc4a68a339c27a54e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.00450v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Grip Stabilization through Independent Finger Tactile Feedback Control

Filipe Veiga, Benoni Edin, Jan Peters
<span title="2020-03-21">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
Such approaches normally rely on object and contact models and do not generalize well to novel manipulation tasks.  ...  Grip force control during robotic in-hand manipulation is usually modeled as a monolithic task, where complex controllers consider the placement of all fingers and the contact states between each finger  ...  1 ), each with a learned predictive model of future slips based on the tactile feedback acquired during finger-object interactions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20061748">doi:10.3390/s20061748</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32245193">pmid:32245193</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nlpndn2rvzdq7hbumbhizrovfy">fatcat:nlpndn2rvzdq7hbumbhizrovfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200325213933/https://res.mdpi.com/d_attachment/sensors/sensors-20-01748/article_deploy/sensors-20-01748.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/92/b4/92b466fb3784b15e258daba757a462a2d4cc43d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20061748"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Toward Sense Making with Grounded Feedback [chapter]

Eliane Stampfer Wiese, Kenneth R. Koedinger
<span title="">2014</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Grounded feedback is one instructional approach proposed to help students integrate conceptual knowledge into their learning of procedures.  ...  Grounded feedback functions primarily by having students take an action in the target domain (often symbolic) and receiving feedback in a representation that is easier to reason with.  ...  While grounded feedback in the fraction addition tutors led to improved long-term learning (pre-to-delayed-test) and improved learning on transfer tasks compared to a correctness-feedback control, none  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07221-0_110">doi:10.1007/978-3-319-07221-0_110</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2o4zy453frdrfapaqd5rtvhwmu">fatcat:2o4zy453frdrfapaqd5rtvhwmu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190428151513/https://s3-eu-west-1.amazonaws.com/pstorage-cmu-348901238291901/12259556/TowardSenseMakingwithGroundedFeedback.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ee/51/ee513c51a11f824fc2f7a0282434e02b6f220f68.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07221-0_110"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Experimental study on parallel and analog optical reservoir computing with delayed feedback system for physical implementation

Tadashi Okumura, Mitsuharu Tai, Masahiko Ando
<span title="">2019</span> <i title="Institute of Electronics, Information and Communications Engineers (IEICE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/o6i5xqmqx5cgjj7ri5se4o5bty" style="color: black;">Nonlinear Theory and Its Applications IEICE</a> </i> &nbsp;
Optical reservoir computing (RC) with delayed feedback is expected to achieve highspeed data processing.  ...  One was two independent benchmark tasks; the other was an integrative multi-input and multi-output odor identification task.  ...  For that reason, we think RC is a promising artificial approaches toward an energy-efficient parallel processor for multi-cognitive tasks simultaneously.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1587/nolta.10.236">doi:10.1587/nolta.10.236</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7uto5ldtzvgybme5tryhxpfdli">fatcat:7uto5ldtzvgybme5tryhxpfdli</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503165915/https://www.jstage.jst.go.jp/article/nolta/10/2/10_236/_pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/65/e36535d3ae1dcbcefddcfcc8031b17b2eae9c1c6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1587/nolta.10.236"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Learning and planning in environments with delayed feedback

Thomas J. Walsh, Ali Nouri, Lihong Li, Michael L. Littman
<span title="2008-07-04">2008</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7rdrzlhoxjb5ho2u76erh6zpni" style="color: black;">Autonomous Agents and Multi-Agent Systems</a> </i> &nbsp;
This work considers the problems of learning and planning in Markovian environments with constant observation and reward delays.  ...  We provide a hardness result for the general planning problem and positive results for several special cases with deterministic or otherwise constrained dynamics.  ...  We thank the First Annual Reinforcement Learning Competition and Adam White.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-008-9056-7">doi:10.1007/s10458-008-9056-7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vsdsrqig3rhankwfoz5w2ejdry">fatcat:vsdsrqig3rhankwfoz5w2ejdry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809053457/http://research.cs.rutgers.edu/~thomaswa/pub/jaamas09Delayed.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/71/9c/719c14406f2d3e2c1d7e3cf632af80653257f32f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-008-9056-7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Creating the Feedback Loop

Adam O. Hebb, Jun Jason Zhang, Mohammad H. Mahoor, Christos Tsiokos, Charles Matlack, Howard Jay Chizeck, Nader Pouratian
<span title="2013-10-23">2014</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rng6dytgc5bkre2aoplt5z3h4u" style="color: black;">Neurosurgery clinics of North America</a> </i> &nbsp;
Current DBS therapy delivers a train of electrical pulses at set stimulation parameters.  ...  This open-loop design is effective for movement disorders, but therapy may be further optimized by a closed loop design.  ...  Seizures detected during stimulation with machine learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.nec.2013.08.006">doi:10.1016/j.nec.2013.08.006</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24262909">pmid:24262909</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4058859/">pmcid:PMC4058859</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cvxhliuwpzhlxoh3buyll62izu">fatcat:cvxhliuwpzhlxoh3buyll62izu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200206084746/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC4058859&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/46/33/4633fa2eac27ad83096408f0851e0bf72ee5d87f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.nec.2013.08.006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4058859" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI [article]

Pragaash Ponnusamy, Clint Solomon Mathialagan, Gustavo Aguilar, Chengyuan Ma, Chenlei Guo
<span title="2022-04-29">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean.  ...  To that end, we propose augmenting the Markov Graph construction with a superposition-based adjacency matrix.  ...  t on the equivalence learning task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.00029v1">arXiv:2205.00029v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/elw2s2frkbeobfr7tukvoyrn7u">fatcat:elw2s2frkbeobfr7tukvoyrn7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220505194818/https://arxiv.org/pdf/2205.00029v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/49/c14969ad8143cc164a925513cf36a2cf7b418c50.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.00029v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-Source Social Feedback of Online News Feeds [article]

Nuno Moniz, Luís Torgo
<span title="2018-01-22">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
machine learning.  ...  This data set is tailored for evaluative comparisons in predictive analytics tasks, although allowing for tasks in other research areas such as topic detection and tracking, sentiment analysis in short  ...  Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) as part of project UID/EEA/50014/2013.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.07055v1">arXiv:1801.07055v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2omuc73le5fwzatipc2z3b2coy">fatcat:2omuc73le5fwzatipc2z3b2coy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013184534/https://arxiv.org/pdf/1801.07055v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/df/fe/dffe8275f2709b4a03354de73679b8601da1a044.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1801.07055v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

LCF: A Deep Learning-Based Lightweight CSI Feedback Scheme for MIMO Networks

Kyu-haeng Lee
<span title="">2022</span> <i title="Computers, Materials and Continua (Tech Science Press)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/amujz7fcqna6do727z6ev3ueo4" style="color: black;">Computers Materials &amp; Continua</a> </i> &nbsp;
State Information (CSI) feedback overhead problem, which can significantly limit Multi-Input Multi-Output (MIMO) beamforming gains.  ...  To address these issues, in this paper, we propose Lightweight CSI Feedback (LCF), a new lightweight CSI feedback scheme.  ...  We propose a novel deep learning-based CSI feedback scheme, LCF, which effectively reduces the CSI feedback overhead by using CSI prediction based on autoregressive LSTM and CSI compression with a convolutional  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.024562">doi:10.32604/cmc.2022.024562</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mr6ec23pibebdm4uavog5fbdsy">fatcat:mr6ec23pibebdm4uavog5fbdsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220301185156/https://www.techscience.com/ueditor/files/cmc/TSP_CMC-71-3/TSP_CMC_24562/TSP_CMC_24562.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/98/18/98189eed1ea81ecbb1c88c48ce2cecb250e92604.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.024562"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 37,384 results