Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat, Hande; Orhan, Guner; Pugeault, Nicolas; Guérin, Frank; Şahi̇n, Erol; Kalkan, Sinan

doi:10.1109/tamd.2015.2476374

Cited by 18 publications

(32 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments, we compare iRBM and diBM against (vanilla) RBM (with the same number of hidden units that was found by iRBM), stacked RBM (with the same number of layers and hidden units as found by siRBM), DBM (with the same number of layers and hidden units as found by diBM), incremental RBM [18], and incremental LDA [6]. In comparing the methods, we use the same number of epochs for each method.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…To get a feeling of the performance of the methods, we looked at the strongest objects associated with the hidden neurons. For this, we just compared one-layer methods (iRBM, incremental RBM [18], incremental LDA [6] and online vanilla RBM) and hence, not considered DBM, diBM, stacked RBM or stacked iRBM, since the first layers of these methods (RBM and iRBM) are included in the comparison. Table I lists the three best (selected by visual inspection) hidden neurons' strongly connected objects for the different methods.…”

Section: Qualitative Inspection Of Context Coherence (Hidden Nodes)mentioning

confidence: 99%

“…1. Although there have been many studies in incremental topic/context modeling in linguistics [4] and robotics [5], [6], they are not hierarchical. There are promising hierarchical topic modeling efforts [7], [8], which however either assume a fixed depth structure or availability of all data at the model construction phase.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Deep Incremental Boltzmann Machine for Modeling Context in Robots

Doğan

Çelikkanat

Kalkan

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Context is an essential capability for robots that are to be as adaptive as possible in challenging environments. Although there are many context modeling efforts, they assume a fixed structure and number of contexts. In this paper, we propose an incremental deep model that extends Restricted Boltzmann Machines. Our model gets one scene at a time, and gradually extends the contextual model when necessary, either by adding a new context or a new context layer to form a hierarchy. We show on a scene classification benchmark that our method converges to a good estimate of the contexts of the scenes, and performs better or on-par on several tasks compared to other incremental models or non-incremental models.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Qualitative Inspection Of Context Coherence (Hidden Nodes)mentioning

confidence: 99%

See 1 more Smart Citation

A Deep Incremental Boltzmann Machine for Modeling Context in Robots

Doğan

Çelikkanat

Kalkan

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, ILSA is on the static datasets, and the dynamic datasets are not considered. Accordingly, we will study on how to building a dynamical partial index for the dynamic term set and document set by integrating existing incremental LSA algorithm [ 61 , 62 ] and incremental SVD algorithm [ 63 – 65 ]. Second, our approach does not pay attention to the transformation process from query into pseudo document which involves lots of unnecessary operations on entries of lower values and increases the execution time of on-line query process.…”

Section: Discussionmentioning

confidence: 99%

An index-based algorithm for fast on-line query processing of latent semantic analysis

Zhang

Wang

2017

PLoS ONE

View full text Add to dashboard Cite

Latent Semantic Analysis (LSA) is widely used for finding the documents whose semantic is similar to the query of keywords. Although LSA yield promising similar results, the existing LSA algorithms involve lots of unnecessary operations in similarity computation and candidate check during on-line query processing, which is expensive in terms of time cost and cannot efficiently response the query request especially when the dataset becomes large. In this paper, we study the efficiency problem of on-line query processing for LSA towards efficiently searching the similar documents to a given query. We rewrite the similarity equation of LSA combined with an intermediate value called partial similarity that is stored in a designed index called partial index. For reducing the searching space, we give an approximate form of similarity equation, and then develop an efficient algorithm for building partial index, which skips the partial similarities lower than a given threshold θ. Based on partial index, we develop an efficient algorithm called ILSA for supporting fast on-line query processing. The given query is transformed into a pseudo document vector, and the similarities between query and candidate documents are computed by accumulating the partial similarities obtained from the index nodes corresponds to non-zero entries in the pseudo document vector. Compared to the LSA algorithm, ILSA reduces the time cost of on-line query processing by pruning the candidate documents that are not promising and skipping the operations that make little contribution to similarity scores. Extensive experiments through comparison with LSA have been done, which demonstrate the efficiency and effectiveness of our proposed algorithm.

show abstract

“…Among these studies, similar to ours, there are also models that explicitly integrate context into a scene model [14,15,17]. For example, Wang et al [14] extend LDA to incorporate relative positions between pixels in a local neighborhood in order to segment an image into semantically meaningful regions.…”

Section: Studymentioning

confidence: 99%

COSMO: Contextualized scene modeling with Boltzmann Machines

Bozcan

Kalkan

2019

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

Scene modeling is very crucial for robots that need to perceive, reason about and manipulate the objects in their environments. In this paper, we adapt and extend Boltzmann Machines (BMs) for contextualized scene modeling. Although there are many models on the subject, ours is the first to bring together objects, relations, and affordances in a highly-capable generative model. For this end, we introduce a hybrid version of BMs where relations and affordances are incorporated with shared, tri-way connections into the model. Moreover, we introduce a dataset for relation estimation and modeling studies. We evaluate our method in comparison with several baselines on object estimation, out-ofcontext object detection, relation estimation, and affordance estimation tasks.Moreover, to illustrate the generative capability of the model, we show several example scenes that the model is able to generate, and demonstrate the benefits of the model on a humanoid robot. The code and the dataset are publicly made available at: https://github.com/bozcani/COSMO

show abstract

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Cited by 18 publications

References 80 publications

A Deep Incremental Boltzmann Machine for Modeling Context in Robots

A Deep Incremental Boltzmann Machine for Modeling Context in Robots

An index-based algorithm for fast on-line query processing of latent semantic analysis

COSMO: Contextualized scene modeling with Boltzmann Machines

Contact Info

Product

Resources

About