arXiv subjects

Ifeoma Nwogu

Publications and source records attributed to Ifeoma Nwogu.

24 records · Page 2Linked to original sources

arXiv2019

Regression with Uncertainty Quantification in Large Scale Complex Data

While several methods for predicting uncertainty on deep networks have been recently proposed, they do not readily translate to large and complex datasets. In this paper we utilize a simplified form of the Mixture Density Networks (MDNs) to produce a one-shot approach to quantify uncertainty in regression problems. We show that our uncertainty bounds are on-par or better than other reported existing methods. When applied to standard regression benchmark datasets, we show an improvement in predictive log-likelihood and root-mean-square-error when compared to existing state-of-the-art methods. We also demonstrate this method's efficacy on stochastic, highly volatile time-series data where stock prices are predicted for the next time interval. The resulting uncertainty graph summarizes significant anomalies in the stock price chart. Furthermore, we apply this method to the task of age estimation from the challenging IMDb-Wiki dataset of half a million face images. We successfully predict the uncertainties associated with the prediction and empirically analyze the underlying causes of the uncertainties. This uncertainty quantification can be used to pre-process low quality datasets and further enable learning.

cs.LG↗

arXiv2018

Computational Social Dynamics: Analyzing the Face-level Interactions in a Group

Interactional synchrony refers to how the speech or behavior of two or more people involved in a conversation become more finely synchronized with each other, and they can appear to behave almost in direct response to one another. Studies have shown that interactional synchrony is a hallmark of relationships, and is produced as a result of rapport. %Research has also shown that up to two-thirds of human communication occurs via nonverbal channels such as gestures (or body movements), facial expressions, \etc. In this work, we use computer vision based methods to extract nonverbal cues, specifically from the face, and develop a model to measure interactional synchrony based on those cues. This paper illustrates a novel method of constructing a dynamic deep neural architecture, specifically made up of intermediary long short-term memory networks (LSTMs), useful for learning and predicting the extent of synchrony between two or more processes, by emulating the nonlinear dependencies between them. On a synthetic dataset, where pairs of sequences were generated from a Gaussian process with known covariates, the architecture could successfully determine the covariance values of the generating process within an error of 0.5% when tested on 100 pairs of interacting signals. On a real-life dataset involving groups of three people, the model successfully estimated the extent of synchrony of each group on a scale of 1 to 5, with an overall prediction mean of $2.96%$ error when performing 5-fold validation, as compared to 26.1% on the random permutations serving as the control baseline.

cs.SI↗

arXiv2016

Dimensionality Reduction with Subspace Structure Preservation

Modeling data as being sampled from a union of independent subspaces has been widely applied to a number of real world applications. However, dimensionality reduction approaches that theoretically preserve this independence assumption have not been well studied. Our key contribution is to show that $2K$ projection vectors are sufficient for the independence preservation of any $K$ class data sampled from a union of independent subspaces. It is this non-trivial observation that we use for designing our dimensionality reduction technique. In this paper, we propose a novel dimensionality reduction algorithm that theoretically preserves this structure for a given dataset. We support our theoretical analysis with empirical results on both synthetic and real world data achieving \textit{state-of-the-art} results compared to popular dimensionality reduction techniques.

cs.LG↗

arXiv2015

Is Joint Training Better for Deep Auto-Encoders?

Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers. This makes it extremely challenging for the model to learn the hidden distribution prior, which in turn leads to a suboptimal model for the data distribution. We therefore investigate joint training of deep autoencoders, where the architecture is viewed as one stack of two or more single-layer autoencoders. A single global reconstruction objective is jointly optimized, such that the objective for the single autoencoders at each layer acts as a local, layer-level regularizer. We empirically evaluate the performance of this joint training scheme and observe that it not only learns a better data model, but also learns better higher layer representations, which highlights its potential for unsupervised feature learning. In addition, we find that the usage of regularizations in the joint training scheme is crucial in achieving good performance. In the supervised setting, joint training also shows superior performance when training deeper models. The joint training framework can thus provide a platform for investigating more efficient usage of different types of regularizers, especially in light of the growing volumes of available unlabeled data.

stat.ML↗

arXiv2014

An Analysis of Random Projections in Cancelable Biometrics

With increasing concerns about security, the need for highly secure physical biometrics-based authentication systems utilizing \emph{cancelable biometric} technologies is on the rise. Because the problem of cancelable template generation deals with the trade-off between template security and matching performance, many state-of-the-art algorithms successful in generating high quality cancelable biometrics all have random projection as one of their early processing steps. This paper therefore presents a formal analysis of why random projections is an essential step in cancelable biometrics. By formally defining the notion of an \textit{Independent Subspace Structure} for datasets, it can be shown that random projection preserves the subspace structure of data vectors generated from a union of independent linear subspaces. The bound on the minimum number of random vectors required for this to hold is also derived and is shown to depend logarithmically on the number of data samples, not only in independent subspaces but in disjoint subspace settings as well. The theoretical analysis presented is supported in detail with empirical results on real-world face recognition datasets.

cs.CV↗

arXiv2014

A Concept Learning Approach to Multisensory Object Perception

This paper presents a computational model of concept learning using Bayesian inference for a grammatically structured hypothesis space, and test the model on multisensory (visual and haptics) recognition of 3D objects. The study is performed on a set of artificially generated 3D objects known as fribbles, which are complex, multipart objects with categorical structures. The goal of this work is to develop a working multisensory representational model that integrates major themes on concepts and concepts learning from the cognitive science literature. The model combines the representational power of a probabilistic generative grammar with the inferential power of Bayesian induction.

cs.CV↗