arXiv subjects

Biswadeep Chakraborty

Publications and source records attributed to Biswadeep Chakraborty.

23 records · Page 2Linked to original sources

arXiv2022

$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search

We present a Model Uncertainty-aware Differentiable ARchiTecture Search ($μ$DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize the concrete dropout probabilities. A predictive variance term is introduced in the validation loss to enable searching for architecture with minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of $μ$DARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from $μ$DARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.

cs.LG↗

arXiv2021

Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networks

A Spiking Neural Network (SNN) is trained with Spike Timing Dependent Plasticity (STDP), which is a neuro-inspired unsupervised learning method for various machine learning applications. This paper studies the generalizability properties of the STDP learning processes using the Hausdorff dimension of the trajectories of the learning algorithm. The paper analyzes the effects of STDP learning models and associated hyper-parameters on the generalizability properties of an SNN. The analysis is used to develop a Bayesian optimization approach to optimize the hyper-parameters for an STDP model for improving the generalizability properties of an SNN.

cs.NE↗

arXiv2021

A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection

This paper proposes a Fully Spiking Hybrid Neural Network (FSHNN) for energy-efficient and robust object detection in resource-constrained platforms. The network architecture is based on Convolutional SNN using leaky-integrate-fire neuron models. The model combines unsupervised Spike Time-Dependent Plasticity (STDP) learning with back-propagation (STBP) learning methods and also uses Monte Carlo Dropout to get an estimate of the uncertainty error. FSHNN provides better accuracy compared to DNN based object detectors while being 150X energy-efficient. It also outperforms these object detectors, when subjected to noisy input data and less labeled training data with a lower uncertainty error.

cs.CV↗

arXiv2021

Cost-aware Feature Selection for IoT Device Classification

Classification of IoT devices into different types is of paramount importance, from multiple perspectives, including security and privacy aspects. Recent works have explored machine learning techniques for fingerprinting (or classifying) IoT devices, with promising results. However, existing works have assumed that the features used for building the machine learning models are readily available or can be easily extracted from the network traffic; in other words, they do not consider the costs associated with feature extraction. In this work, we take a more realistic approach, and argue that feature extraction has a cost, and the costs are different for different features. We also take a step forward from the current practice of considering the misclassification loss as a binary value, and make a case for different losses based on the misclassification performance. Thereby, and more importantly, we introduce the notion of risk for IoT device classification. We define and formulate the problem of cost-aware IoT device classification. This being a combinatorial optimization problem, we develop a novel algorithm to solve it in a fast and effective way using the Cross-Entropy (CE) based stochastic optimization technique. Using traffic of real devices, we demonstrate the capability of the CE based algorithm in selecting features with minimal risk of misclassification while keeping the cost for feature extraction within a specified limit.

cs.NI↗

arXiv2019

Design and Evaluation of Self-Assembled Actin-Based Nano-Communication

The tremendous progress in nanotechnology over the last century, makes it possible to engineer tiny nanodevices, which they need a nano-communication network to interact. Two solutions are proposed in literature to create a nano-communication system, either by using the classical electromagnetic paradigm with Terahertz band, or using the bio-inspired molecular communication. However, Terahertz is suffering from molecular absorption and scattering losses at nano level, and the achievable throughput of molecular communication is very low. In this paper, we propose a new solution to establish a wired nano-communication. Self-assembled actin-based is a new method that takes advantage of actin filaments self-assembly to create a nano wire between a transmitter and a receiver, and use electrons as information carriers. VPython framework is used in this paper to perform stochastic simulations of the nano wire formation. The algorithms used for the simulations are presented. The stability of the constructed nano wire is analyzed, and the error probability is calculated. Self-assembled actin-based method promises a fast and stable nano-communication system with a very high achievable throughput.

cs.ET↗