arXiv subjects

S. Fernando

Publications and source records attributed to S. Fernando.

5 recordsLinked to original sources

arXiv2022

Interpretability and accessibility of machine learning in selected food processing, agriculture and health applications

Artificial Intelligence (AI) and its data-centric branch of machine learning (ML) have greatly evolved over the last few decades. However, as AI is used increasingly in real world use cases, the importance of the interpretability of and accessibility to AI systems have become major research areas. The lack of interpretability of ML based systems is a major hindrance to widespread adoption of these powerful algorithms. This is due to many reasons including ethical and regulatory concerns, which have resulted in poorer adoption of ML in some areas. The recent past has seen a surge in research on interpretable ML. Generally, designing a ML system requires good domain understanding combined with expert knowledge. New techniques are emerging to improve ML accessibility through automated model design. This paper provides a review of the work done to improve interpretability and accessibility of machine learning in the context of global problems while also being relevant to developing countries. We review work under multiple levels of interpretability including scientific and mathematical interpretation, statistical interpretation and partial semantic interpretation. This review includes applications in three areas, namely food processing, agriculture and health.

cs.LG↗

arXiv2018

Wavelet based edge feature enhancement for convolutional neural networks

Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two wavelet-based edge feature enhancement methods to preprocess the input images to convolutional neural networks. The first method develops feature enhanced representations by decomposing the input images using wavelet transform and limited reconstructing subsequently. The second method develops such feature enhanced inputs to the network using local modulus maxima of wavelet coefficients. For each method, we have developed a new preprocessing layer by implementing each purposed method and have appended to the network architecture. Our empirical evaluations demonstrate that the proposed methods are outperforming the baselines and previously published work with significant accuracy gains.

cs.CV↗

arXiv2018

On Optimizing Deep Convolutional Neural Networks by Evolutionary Computing

Optimization for deep networks is currently a very active area of research. As neural networks become deeper, the ability in manually optimizing the network becomes harder. Mini-batch normalization, identification of effective respective fields, momentum updates, introduction of residual blocks, learning rate adoption, etc. have been proposed to speed up the rate of convergent in manual training process while keeping the higher accuracy level. However, the problem of finding optimal topological structure for a given problem is becoming a challenging task need to be addressed immediately. Few researchers have attempted to optimize the network structure using evolutionary computing approaches. Among them, few have successfully evolved networks with reinforcement learning and long-short-term memory. A very few has applied evolutionary programming into deep convolution neural networks. These attempts are mainly evolved the network structure and then subsequently optimized the hyper-parameters of the network. However, a mechanism to evolve the deep network structure under the techniques currently being practiced in manual process is still absent. Incorporation of such techniques into chromosomes level of evolutionary computing, certainly can take us to better topological deep structures. The paper concludes by identifying the gap between evolutionary based deep neural networks and deep neural networks. Further, it proposes some insights for optimizing deep neural networks using evolutionary computing techniques.

cs.NE↗

arXiv2004

Oscillator Construction of Spectra of PP-Wave Superalgebras in Eleven Dimensions

After reviewing the oscillator realization of the symmetry superalgebra of the BMN matrix model on its maximally supersymmetric plane-wave background and the construction of its zero-mode spectrum, we study a large number of non-maximally supersymmetric pp-wave algebras in eleven dimensions which are obtained by various restrictions from the maximally supersymmetric case (BMN model). We also show how to obtain their zero-mode spectra, which we explicitly construct in some chosen examples. Except for some `exotic' or degenerate special cases, we believe our study covers all possible interesting pp-wave superalgebras of this kind in eleven dimensions.

hep-th↗

arXiv2001

Twisted Kac-Moody Algebras And The Entropy Of AdS$_3$ Black Hole

We show that an $SL(2,R)_L \times SL(2,R)_R$ Chern-Simons theory coupled to a source on a manifold with the topology of a disk correctly describes the entropy of the AdS$_3$ black hole. The resulting boundary WZNW theory leads to two copies of a twisted Kac-Moody algebra, for which the respective Virasoro algebras have the same central charge $c$ as the corresponding untwisted theory. But the eigenvalues of the respective $L_0$ operators are shifted. We show that the asymptotic density of states for this theory is, up to logarithmic corrections, the same as that obtained by Strominger using the asymptotic symmetry of Brown and Henneaux.

hep-th↗