734 Hits in 1.3 sec

Association Analysis Techniques for Discovering Functional Modules from Microarray Data

Gaurav Pandey, Gaurav Pandey, Gowtham Atluri, Michael Steinbach, Vipin Kumar
2008 Nature Precedings  
doi:10.1038/npre.2008.2184 fatcat:7dr5573uwzbajbpllcyi42emdm

Unsupervised feature learning with discriminative encoder [article]

Gaurav Pandey, Ambedkar Dukkipati
2017 arXiv   pre-print
In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of labeled data. How can one use the same discriminative models for learning useful features in the absence of labels? We address this question in this paper, by jointly modeling the distribution of data and latent features in a manner that explicitly assigns
more » ... o probability to unobserved data. Rather than maximizing the marginal probability of observed data, we maximize the joint probability of the data and the latent features using a two step EM-like procedure. To prevent the model from overfitting to our initial selection of latent features, we use adversarial regularization. Depending on the task, we allow the latent features to be one-hot or real-valued vectors and define a suitable prior on the features. For instance, one-hot features correspond to class labels and are directly used for the unsupervised and semi-supervised classification task, whereas real-valued feature vectors are fed as input to simple classifiers for auxiliary supervised discrimination tasks. The proposed model, which we dub discriminative encoder (or DisCoder), is flexible in the type of latent features that it can capture. The proposed model achieves state-of-the-art performance on several challenging tasks.
arXiv:1709.00672v1 fatcat:miomvooxefcj7ekfa3ojpk2pzq

To go deep or wide in learning? [article]

Gaurav Pandey, Ambedkar Dukkipati
2014 arXiv   pre-print
To achieve acceptable performance for AI tasks, one can either use sophisticated feature extraction methods as the first layer in a two-layered supervised learning model, or learn the features directly using a deep (multi-layered) model. While the first approach is very problem-specific, the second approach has computational overheads in learning multiple layers and fine-tuning of the model. In this paper, we propose an approach called wide learning based on arc-cosine kernels, that learns a
more » ... gle layer of infinite width. We propose exact and inexact learning strategies for wide learning and show that wide learning with single layer outperforms single layer as well as deep architectures of finite width for some benchmark datasets.
arXiv:1402.5634v1 fatcat:o6dzmdqmijahrlwlfpyjqcata4

Discriminative Neural Topic Models [article]

Gaurav Pandey, Ambedkar Dukkipati
2017 arXiv   pre-print
We propose a neural network based approach for learning topics from text and image datasets. The model makes no assumptions about the conditional distribution of the observed features given the latent topics. This allows us to perform topic modelling efficiently using sentences of documents and patches of images as observed features, rather than limiting ourselves to words. Moreover, the proposed approach is online, and hence can be used for streaming data. Furthermore, since the approach
more » ... es neural networks, it can be implemented on GPU with ease, and hence it is very scalable.
arXiv:1701.06796v2 fatcat:r7ly6dgyxffxpec7qe4oiirzxm

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Sean Whalen, Om Prakash Pandey, Gaurav Pandey
2016 Methods  
We explored the first two aspects in our previous work on this problem (Whalen and Pandey (2013) ).  ...  Introduction Prediction problems in biomedical sciences, including protein function prediction (PFP) (Pandey et al. (2006) ; Sharan et al. (2007) ), are generally quite difficult.  ... 
doi:10.1016/j.ymeth.2015.08.016 pmid:26342255 pmcid:PMC4718788 fatcat:dwg3lg5rxfe3tntrzdibfucpqe

Fighting Neuroblastomas with NBAT1

Gaurav Kumar Pandey, Chandrasekhar Kanduri
2015 Oncoscience  
Fighting Neuroblastomas with NBAT1 Gaurav Kumar Pandey and Chandrasekhar Kanduri Children are vulnerable to extracranial solid tumours, known as neuroblastomas, at a very young age.  ... 
doi:10.18632/oncoscience.126 pmid:25859549 pmcid:PMC4381699 fatcat:uk5jb5iv2bfa3hx3ecxlol6pl4

A Survey: Various Techniques of Image Compression [article]

Gaurav Vijayvargiya, Sanjay Silakari, Rajeev Pandey
2013 arXiv   pre-print
(sponsors) Gaurav Vijayvargiya Dr.  ...  Sanjay Silakari Dr.Rajeev Pandey Dept. of CSE Dept. of CSE Dept. of CSE UIT-RGPV UIT-RGPV UIT-RGPV Bhopal, India Bhopal, India Bhopal, India  ... 
arXiv:1311.6877v1 fatcat:xa27aklg4ndctgs6uwvfqcgpxe

Long noncoding RNAs and neuroblastoma

Gaurav Kumar Pandey, Chandrasekhar Kanduri
2015 OncoTarget  
Similar to lncUSMycN, a more recent study by Pandey et al has also reported a novel transcript on chromosome arm 2p.  ...  The study by Pandey et al suggests, there is an intricate interplay of multiple factors that underlay the differential expression of NBAT1 in NB tumours (Figure 2A ) [17] .  ... 
doi:10.18632/oncotarget.4251 pmid:26087192 pmcid:PMC4621889 fatcat:p7am7op62vbqlb43f3wkxgjm7i

Unsupervised Learning of Interpretable Dialog Models [article]

Dhiraj Madan, Dinesh Raghu, Gaurav Pandey, Sachindra Joshi
2018 arXiv   pre-print
Recently several deep learning based models have been proposed for end-to-end learning of dialogs. While these models can be trained from data without the need for any additional annotations, it is hard to interpret them. On the other hand, there exist traditional state based dialog systems, where the states of the dialog are discrete and hence easy to interpret. However these states need to be handcrafted and annotated in the data. To achieve the best of both worlds, we propose Latent State
more » ... cking Network (LSTN) using which we learn an interpretable model in unsupervised manner. The model defines a discrete latent variable at each turn of the conversation which can take a finite set of values. Since these discrete variables are not present in the training data, we use EM algorithm to train our model in unsupervised manner. In the experiments, we show that LSTN can help achieve interpretability in dialog models without much decrease in performance compared to end-to-end approaches.
arXiv:1811.01012v1 fatcat:xfm3pnxoa5fz5g53gb5d62nnfq

Mask Focus: Conversation Modelling by Learning Concepts [article]

Gaurav Pandey, Dinesh Raghu, Sachindra Joshi
2020 arXiv   pre-print
Pandey et al. (2018) proposed to ground the generated response in a set of retrieved responses. Liu et al. (2018) incorporated external knowledge to guide response generation in a dialog.  ... 
arXiv:2003.04976v1 fatcat:j7kvsalsbbdxve2sbtsvuaa6eu

Ford Multi-AV Seasonal Dataset [article]

Siddharth Agarwal, Ankit Vora, Gaurav Pandey, Wayne Williams, Helen Kourous, James McBride
2020 arXiv   pre-print
We use the method described in Pandey et al. (2012) . This is a mutual information based algorithm that provides a relative transformation from the camera to the lidar (X cl ).  ...  Pandey et al. (2011) retrofitted a Ford F-250 pickup truck with HDL-64E lidar, Point grey Ladybug3 omnidirectional camera, Riegl LMS-Q120 lidar, Applanix POS LV and Xsens MTi-G IMU to release one of the  ... 
arXiv:2003.07969v1 fatcat:fn45licsn5gw3auad5mbq6bf6i

Targeted therapy of gastrointestinal stromal tumours

Ashish Jakhetiya, Pankaj Kumar Garg, Gaurav Prakash, Jyoti Sharma, Rambha Pandey, Durgatosh Pandey
2016 World Journal of Gastrointestinal Surgery  
Gastrointestinal stromal tumours (GISTs) are mesen chymal neoplasms originating in the gastrointestinal tract, usually in the stomach or the small intestine, and rarely elsewhere in the abdomen. The malignant potential of GISTs is variable ranging from small lesions with a benign behaviour to fatal sarcomas. The majo rity of the tumours stain positively for the CD117 (KIT) and discovered on GIST1 (DOG1 or anoctamin 1) expression, and they are characterized by the presence of a driver
more » ... ating mutation in either KIT or plateletderived growth factor receptor α. Although surgery is the primary modality of treatment, almost half of the patients have disease recurrence following surgery, which highlights the need for an effective adjuvant therapy. Traditionally, GISTs are considered chemotherapy and radiotherapy resistant. With the advent of targeted therapy (tyrosine kinase inhibitors), there has been a paradigm shift in the management of GISTs in the last decade. We present a comprehensive review of targeted therapy in the management of GISTs.
doi:10.4240/wjgs.v8.i5.345 pmid:27231512 pmcid:PMC4872062 fatcat:lhzrjjdr2zgera6ywnzeocdwle

Aerial Imagery based LIDAR Localization for Autonomous Vehicles [article]

Ankit Vora, Siddharth Agarwal, Gaurav Pandey, James McBride
2020 arXiv   pre-print
In Fig. 7 : 7 Localization Ankit Vora and Siddharth Agarwal are with Ford AV LLC, Dearborn, MI, USA {avora3,sagarw20} Gaurav Pandey and James McBride are with Ford Motor Company, Dearborn,  ... 
arXiv:2003.11192v1 fatcat:thsizvjxyrh7bbikdb2cg3jckm

A Comparative Analysis of Ensemble Classifiers: Case Studies in Genomics [article]

Sean Whalen, Gaurav Pandey
2013 arXiv   pre-print
To address this problem, Pandey et al.  ...  These datasets are publicly available from Pandey et al.  ... 
arXiv:1309.5047v1 fatcat:vfi2pfkg65fwvbui4q7sl2zple

Application of student's t-test, analysis of variance, and covariance

Prabhaker Mishra, Uttam Singh, ChandraM Pandey, Priyadarshni Mishra, Gaurav Pandey
2019 Annals of Cardiac Anaesthesia  
Student's t test (t test), analysis of variance (ANOVA), and analysis of covariance (ANCOVA) are statistical methods used in the testing of hypothesis for comparison of means between the groups. The Student's t test is used to compare the means between two groups, whereas ANOVA is used to compare the means among three or more groups. In ANOVA, first gets a common P value. A significant P value of the ANOVA test indicates for at least one pair, between which the mean difference was statistically
more » ... significant. To identify that significant pair(s), we use multiple comparisons. In ANOVA, when using one categorical independent variable, it is called one-way ANOVA, whereas for two categorical independent variables, it is called two-way ANOVA. When using at least one covariate to adjust with dependent variable, ANOVA becomes ANCOVA. When the size of the sample is small, mean is very much affected by the outliers, so it is necessary to keep sufficient sample size while using these methods.
doi:10.4103/aca.aca_94_19 pmid:31621677 pmcid:PMC6813708 fatcat:auytfsxg5nfapdsekyi3rzqrim
« Previous Showing results 1 — 15 out of 734 results