Filters








24,748 Hits in 4.5 sec

A Reinforcement Learning Assisted Eye-Driven Computer Game Employing a Decision Tree-Based Approach and CNN Classification

Joao Perdiz, Luis Garrote, Gabriel Pires, Urbano J. Nunes
2021 IEEE Access  
Finally, a Reinforcement Learning-based game actuation approach simultaneously updates multiple (State, Action) pairs for each rewarded outcome, intervenes to mitigate the consequences of wrongful game  ...  In the proposed framework, an Electrooculography (EOG)-based game is operated through a pipeline of decision methods.  ...  For each class, a set of rules describes either a sequence that benefits the decision toward that class, or the affirmation or denial of an Event class.  ... 
doi:10.1109/access.2021.3068055 fatcat:rwet3gnqgzheni5nemwdm56jrm

Clear Visual Separation of Temporal Event Sequences

Andreas Mathisen, Kaj GrOnbak
2017 2017 IEEE Visualization in Data Science (VDS)  
Extracting and visualizing informative insights from temporal event sequences becomes increasingly difficult when data volume and variety increase.  ...  We compare composite event learning with two approaches for extracting event patterns using real world company event data from an ongoing project with the Danish Business Authority.  ...  Segmentation: Divide each temporal event sequence into equal time segments of size w.  ... 
doi:10.1109/vds.2017.8573439 fatcat:eqtwengr5jfyldpnaa5zs24hf4

Clear Visual Separation of Temporal Event Sequences [article]

Andreas Mathisen Department of Computer Science, Aarhus University)
2017 arXiv   pre-print
Extracting and visualizing informative insights from temporal event sequences becomes increasingly difficult when data volume and variety increase.  ...  We compare composite event learning with two approaches for extracting event patterns using real world company event data from an ongoing project with the Danish Business Authority.  ...  Segmentation: Divide each temporal event sequence into equal time segments of size w.  ... 
arXiv:1710.06291v1 fatcat:igqmmxefjndcnejjjlnrux725u

Learning Temporal Causal Sequence Relationships [article]

Antonio Anastasio Bruto da Costa, Pallab Dasgupta
2020 arXiv   pre-print
We make use of decision trees and interval arithmetic to mine sequences that explain defining events in the time-series.  ...  We propose modified decision tree construction metrics to handle the non-determinism introduced by the temporal dimension.  ...  Introduction This article presents an approach for learning causal sequence relationships, in the form of temporal properties, from data.  ... 
arXiv:1905.12262v5 fatcat:rx4ao2cpevcwtgqhwaclswvkfa

Top-down Discourse Parsing via Sequence Labelling [article]

Fajri Koto and Jey Han Lau and Timothy Baldwin
2021 arXiv   pre-print
By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space  ...  We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020).  ...  As a result, there has recently been a move towards top-down approaches (Kobayashi et al., 2020; Zhang et al., 2020) .  ... 
arXiv:2102.02080v2 fatcat:t6d5nm5wufgp3kq2nmj4vqf7su

Temporal Attention-Gated Model for Robust Sequence Classification [article]

Wenjie Pei, Tadas Baltrušaitis, David M.J. Tax, Louis-Philippe Morency
2017 arXiv   pre-print
An important advantage of our approach is interpretability since the temporal attention weights provide a meaningful value for the salience of each time step in the sequence.  ...  We then use a novel gated recurrent network to learn the hidden representation for the final prediction.  ...  Consequently, TAGM's classification decision is made based on the selected relevant segments, improving accuracy over the conventional models that take into account the whole input sequence.  ... 
arXiv:1612.00385v2 fatcat:wyz7xw2p5naxpivviru22ysdl4

Seamless Execution of Action Sequences

Freek Stulp, Wolfram Koska, Alexis Maldonado, Michael Beetz
2007 Engineering of Complex Computer Systems (ICECCS), Proceedings of the IEEE International Conference on  
We then present subgoal refinement, a procedure that optimizes action sequences.  ...  This performance is computed using action models, which are learned from observed experience.  ...  Model trees are a generalization of decision trees, in which the nominal values at the leaf nodes are replaced by line segments. For more information on model trees, we refer to [10] and [13] .  ... 
doi:10.1109/robot.2007.364043 dblp:conf/icra/StulpKMB07 fatcat:hlq5pg6jazborpqhiesfywomvy

Relational Sequence Learning [chapter]

Kristian Kersting, Luc De Raedt, Bernd Gutmann, Andreas Karwath, Niels Landwehr
2008 Lecture Notes in Computer Science  
Applying traditional sequential learning techniques to such relational sequences requires either to ignore the internal structure or to put up with a combinatorial explosion in the model complexity.  ...  Sequential behavior and sequence learning is essential to intelligence. Often the elements of sequences exhibit an internal structure that can elegantly be represented using relational atoms.  ...  Each regression tree stands for a gradient and the sum of all for the potential function. We adapted Dietterich et al.'s Gradient Tree Boosting approach, called TreeCRF, to learn the trees.  ... 
doi:10.1007/978-3-540-78652-8_2 fatcat:g3uiv73q4ndn7dkp57o7obpcdy

Curvature: A signature for Action Recognition in Video Sequences [article]

He Chen, Gregory S. Chirikjian
2019 arXiv   pre-print
In this paper, a novel signature of human action recognition, namely the curvature of a video sequence, is introduced.  ...  Once such curvatures are obtained, statistical indexes are extracted and fed into a learning-based classifier. Overall, our method is simple but powerful.  ...  learning, whose component is decision trees.  ... 
arXiv:1904.13003v2 fatcat:sguopc43inewpedemgkqok462i

Temporal Attention-Gated Model for Robust Sequence Classification

Wenjie Pei, Tadas Baltrusaitis, David M. J. Tax, Louis-Philippe Morency
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
An important advantage of our approach is interpretability since the temporal attention weights provide a meaningful value for the salience of each time step in the sequence.  ...  We then use a novel gated recurrent network to learn the hidden representation for the final prediction.  ...  Consequently, TAGM's classification decision is made based on the selected relevant segments, improving accuracy over the conventional models that take into account the whole input sequence.  ... 
doi:10.1109/cvpr.2017.94 dblp:conf/cvpr/PeiBTM17 fatcat:brdpjt6mivczhmrylcmkiwej5u

Tackling Sequence to Sequence Mapping Problems with Neural Networks [article]

Lei Yu
2018 arXiv   pre-print
A lot of research has been devoted to finding ways of tackling these problems, with traditional approaches relying on a combination of hand-crafted features, alignment models, segmentation heuristics,  ...  In Natural Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence.  ...  Heilman and Smith (2010) used a tree kernel as a heuristic to search for the minimal edit sequences between parse trees.  ... 
arXiv:1810.10802v1 fatcat:qi5xhkzv6bh5njfzd5pos4dnpq

Facial expression recognition from video sequences: temporal and static modeling

Ira Cohen, Nicu Sebe, Ashutosh Garg, Lawrence S. Chen, Thomas S. Huang
2003 Computer Vision and Image Understanding  
We exploit the existing methods and propose a new architecture of hidden Markov models (HMMs) for automatically segmenting and recognizing human facial expression from video sequences.  ...  We also introduce a facial expression recognition from live video input using temporal cues.  ...  In reality, this segmentation is not available, and therefore there is a need to find an automatic way of segmenting the sequences.  ... 
doi:10.1016/s1077-3142(03)00081-x fatcat:ytclrandfvhermade25wlqb2a4

A Unified Theoretical Framework for Cognitive Sequencing

Tejas Savalia, Anuj Shukla, Raju S. Bapi
2016 Frontiers in Psychology  
Keywords: implicit sequence learning, explicit sequence knowledge, habitual and goal-directed behavior, modelfree vs. model-based learning, hierarchical reinforcement learning  ...  We show how the computational principles of model-free and model-based learning paradigms, along with a pivotal role for attention and awareness, offer a unifying framework for these two dichotomies.  ...  A model-based mechanism conceives this as building a search tree leading toward goal states.  ... 
doi:10.3389/fpsyg.2016.01821 pmid:27917146 pmcid:PMC5114455 fatcat:vsplfs4rx5hnnbzybsv4zn3ihq

Survey on Visual Analysis of Event Sequence Data [article]

Yi Guo, Shunan Guo, Zhuochen Jin, Smiti Kaul, David Gotz, Nan Cao
2020 arXiv   pre-print
Event sequence data record series of discrete events in the time order of occurrence.  ...  techniques to extract and communicate insights from event sequence datasets.  ...  However, interpretability is recognized as a primary challenge of deep learning approaches.  ... 
arXiv:2006.14291v1 fatcat:zmlsmiabzbec5cbtoltk3yc3oe

Speech recognition by indexing and sequencing

Simone Franzini, Jezekiel Ben-Arie
2010 2010 International Conference of Soft Computing and Pattern Recognition  
In our current approach, we improved on this by using a kd-tree (k-dimensional tree) (40) , an extension of a binary tree to multiple dimensions.  ...  (DTW) (2) is a non-parametric technique that matches temporal or spatial sequences.  ... 
doi:10.1109/socpar.2010.5686409 dblp:conf/socpar/FranziniB10 fatcat:zqeoozazrnbozj3a5tgj7lk2qe
« Previous Showing results 1 — 15 out of 24,748 results