no code implementations • 19 Apr 2024 • Harshit Kumar, Sudarshan Sharma, Biswadeep Chakraborty, Saibal Mukhopadhyay
This study introduces RT-HMD, a Hardware-based Malware Detector (HMD) for mobile devices, that refines malware representation in segmented time-series through a Multiple Instance Learning (MIL) approach.
no code implementations • 9 Apr 2024 • Beomseok Kang, Harshit Kumar, Minah Lee, Biswadeep Chakraborty, Saibal Mukhopadhyay
Locally interacting dynamical systems, such as epidemic spread, rumor propagation through crowd, and forest fire, exhibit complex global dynamics originated from local, relatively simple, and often stochastic interactions between dynamic elements.
no code implementations • 19 Mar 2024 • Biswadeep Chakraborty, Saibal Mukhopadhyay
Recent work by \cite{barannikov2021representation} has introduced a novel method to compare topological mappings of learned representations called Representation Topology Divergence (RTD).
no code implementations • 6 Mar 2024 • Biswadeep Chakraborty, Beomseok Kang, Harshit Kumar, Saibal Mukhopadhyay
We show that the LNP can leverage diversity in neuronal timescales to design a sparse Heterogeneous RSNN (HRSNN).
no code implementations • 23 Feb 2024 • Harshit Kumar, Biswadeep Chakraborty, Beomseok Kang, Saibal Mukhopadhyay
We identify the Expected Calibration Error (ECE) as a robust metric that tests the proposed evaluation criteria, offering asymptotic guarantees of proper scoring rules and improved interpretability through calibration curves.
no code implementations • 10 Apr 2023 • Biswadeep Chakraborty, Saibal Mukhopadhyay
Energy and data-efficient online time series prediction for predicting evolving dynamical systems are critical in several fields, especially edge AI applications that need to update continuously based on streaming data.
no code implementations • 22 Feb 2023 • Biswadeep Chakraborty, Saibal Mukhopadhyay
This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning.
no code implementations • 22 Feb 2023 • Beomseok Kang, Biswadeep Chakraborty, Saibal Mukhopadhyay
We present an unsupervised deep learning model for 3D object classification.
no code implementations • 28 Oct 2022 • Beomseok Kang, Minah Lee, Harshit Kumar, Saibal Mukhopadhyay
As an example, we consider a forest fire model where we aim to predict when a particular tree agent will start burning.
no code implementations • 22 Sep 2022 • Biswadeep Chakraborty, Saibal Mukhopadhyay
Spiking Neural Networks are often touted as brain-inspired learning models for the third wave of Artificial Intelligence.
no code implementations • 19 Aug 2022 • Beomseok Kang, Saibal Mukhopadhyay
In this light, clustering the agents in the game has been used for various purposes such as the efficient control of the agents in multi-agent reinforcement learning and game analytic tools for the game users.
no code implementations • 11 Aug 2022 • Saurabh Dash, Xueyuan She, Saibal Mukhopadhyay
We present a novel Recurrent Graph Network (RGN) approach for predicting discrete marked event sequences by learning the underlying complex stochastic process.
no code implementations • 13 Jul 2022 • Beomseok Kang, Harshit Kumar, Saurabh Dash, Saibal Mukhopadhyay
Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system.
no code implementations • 3 Jun 2022 • Hemant Kumawat, Saibal Mukhopadhyay
In particular, our method improves the perception of small and long range objects, which are often not detected by the object detectors in RGB mode.
no code implementations • 30 Apr 2022 • Burhan A. Mudassar, Sho Ko, Maojingjing Li, Priyabrata Saha, Saibal Mukhopadhyay
For the high ranking camera videos we show that the accuracy of action detection is decreased.
1 code implementation • 16 Mar 2022 • Priyabrata Saha, Saibal Mukhopadhyay
In this paper, we address the problem of predicting complex, nonlinear spatiotemporal dynamics when available data is recorded at irregularly-spaced sparse spatial locations.
no code implementations • ICLR 2022 • Xueyuan She, Saurabh Dash, Saibal Mukhopadhyay
Moreover, we prove that heterogeneous neurons with varying dynamics and skip-layer connections improve sequence approximation using feedforward SNN.
Ranked #1 on Image Classification on N-Caltech 101
no code implementations • 24 Jul 2021 • Biswadeep Chakraborty, Saibal Mukhopadhyay
We present a Model Uncertainty-aware Differentiable ARchiTecture Search ($\mu$DARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty.
Ranked #12 on Neural Architecture Search on CIFAR-100
no code implementations • 31 May 2021 • Biswadeep Chakraborty, Saibal Mukhopadhyay
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.
no code implementations • 25 May 2021 • Nathan Eli Miller, Saibal Mukhopadhyay
In this work, we present a Quantum Hopfield Associative Memory (QHAM) and demonstrate its capabilities in simulation and hardware using IBM Quantum Experience.
no code implementations • 21 Apr 2021 • Biswadeep Chakraborty, Xueyuan She, Saibal Mukhopadhyay
This paper proposes a Fully Spiking Hybrid Neural Network (FSHNN) for energy-efficient and robust object detection in resource-constrained platforms.
no code implementations • 21 Mar 2021 • Harshit Kumar, Nikhil Chawla, Saibal Mukhopadhyay
Hardware-based Malware Detectors (HMDs) using Machine Learning (ML) models have shown promise in detecting malicious workloads.
no code implementations • 30 Nov 2020 • Priyabrata Saha, Saibal Mukhopadhyay
In this paper, we consider the problem of learning prediction models for spatiotemporal physical processes driven by unknown partial differential equations (PDEs).
1 code implementation • 24 Sep 2020 • Priyabrata Saha, Magnus Egerstedt, Saibal Mukhopadhyay
The proposed method relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law.
1 code implementation • 14 Apr 2020 • Priyabrata Saha, Saurabh Dash, Saibal Mukhopadhyay
Spatio-temporal dynamics of physical processes are generally modeled using partial differential equations (PDEs).
1 code implementation • 24 Jan 2020 • Priyabrata Saha, Arslan Ali, Burhan A. Mudassar, Yun Long, Saibal Mukhopadhyay
We present the MagNet, a neural network-based multi-agent interaction model to discover the governing dynamics and predict evolution of a complex multi-agent system from observations.
no code implementations • 25 Sep 2019 • Xueyuan She, Priyabrata Saha, Daehyun Kim, Yun Long, Saibal Mukhopadhyay
We present a Deep Neural Network with Spike Assisted Feature Extraction (SAFE-DNN) to improve robustness of classification under stochastic perturbation of inputs.
no code implementations • 11 Sep 2019 • Xueyuan She, Yun Long, Daehyun Kim, Saibal Mukhopadhyay
ScieNet integrates unsupervised learning using spiking neural network (SNN) for unsupervised contextual informationextraction with a back-end DNN trained for classification.
no code implementations • 11 Sep 2019 • Xueyuan She, Yun Long, Saibal Mukhopadhyay
In addition, we show that the new algorithm can be used for designing a robust ReRAM based SNN accelerator that has strong resilience to device variation.
no code implementations • 9 Jul 2019 • Nikhil Chawla, Arvind Singh, Monodeep Kar, Saibal Mukhopadhyay
The proliferation of ubiquitous computing requires energy-efficient as well as secure operation of modern processors.
no code implementations • ICLR 2019 • Taesik Na, Minah Lee, Burhan A. Mudassar, Priyabrata Saha, Jong Hwan Ko, Saibal Mukhopadhyay
We evaluate our proposed method for various machine learning tasks including object detection on MS-COCO 2014 dataset, multiple object tracking problem on MOT-Challenge dataset, and human activity classification on UCF 101 dataset.
no code implementations • 19 Jun 2018 • Yun Long, Xueyuan She, Saibal Mukhopadhyay
In this paper, we present HybridNet, a framework that integrates data-driven deep learning and model-driven computation to reliably predict spatiotemporal evolution of a dynamical systems even with in-exact knowledge of their parameters.
no code implementations • 16 Mar 2018 • Bahar Asgari, Saibal Mukhopadhyay, Sudhakar Yalamanchili
However, these efforts ignored maintaining a balance between bandwidth and compute rate of an architecture, with those of applications, which is a key principle in designing scalable large systems.
Hardware Architecture Performance
no code implementations • 11 Feb 2018 • Jong Hwan Ko, Taesik Na, Mohammad Faisal Amir, Saibal Mukhopadhyay
The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform.
no code implementations • 12 Oct 2017 • Duckhwan Kim, Taesik Na, Sudhakar Yalamanchili, Saibal Mukhopadhyay
This paper presents, NeuroTrainer, an intelligent memory module with in-memory accelerators that forms the building block of a scalable architecture for energy efficient training for deep neural networks.
Hardware Architecture
1 code implementation • ICLR 2018 • Taesik Na, Jong Hwan Ko, Saibal Mukhopadhyay
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks.