Search Results for author:
Found 36 papers, 5 papers with code
Towards Robust Real-Time Hardware-based Mobile Malware Detection using Multiple Instance Learning Formulation
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.
Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction
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.
Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networks
Recent work by \cite{barannikov2021representation} has introduced a novel method to compare topological mappings of learned representations called Representation Topology Divergence (RTD).
Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
We show that the LNP can leverage diversity in neuronal timescales to design a sparse Heterogeneous RSNN (HRSNN).
Studying the Impact of Stochasticity on the Evaluation of Deep Neural Networks for Forest-Fire Prediction
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.
Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Prediction
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.
Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
We present an unsupervised deep learning model for 3D object classification.
Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles
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.
Forecasting Local Behavior of Self-organizing Many-agent System without Reconstruction
As an example, we consider a forest fire model where we aim to predict when a particular tree agent will start burning.
Heterogeneous Recurrent Spiking Neural Network for Spatio-Temporal Classification
Spiking Neural Networks are often touted as brain-inspired learning models for the third wave of Artificial Intelligence.
Forecasting Evolution of Clusters in Game Agents with Hebbian Learning
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.
Learning Point Processes using Recurrent Graph Network
We present a novel Recurrent Graph Network (RGN) approach for predicting discrete marked event sequences by learning the underlying complex stochastic process.
Unsupervised Hebbian Learning on Point Sets in StarCraft II
Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system.
Radar Guided Dynamic Visual Attention for Resource-Efficient RGB Object Detection
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.
RADNet: A Deep Neural Network Model for Robust Perception in Moving Autonomous Systems
For the high ranking camera videos we show that the accuracy of action detection is decreased.
Unraveled Multilevel Transformation Networks for Predicting Sparsely-Observed Spatiotemporal Dynamics
In this paper, we address the problem of predicting complex, nonlinear spatiotemporal dynamics when available data is recorded at irregularly-spaced sparse spatial locations.
Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods
Moreover, we prove that heterogeneous neurons with varying dynamics and skip-layer connections improve sequence approximation using feedforward SNN.
Ranked #1 on
Gesture Recognition
on DVS128 Gesture
$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search
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
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.
A Quantum Hopfield Associative Memory Implemented on an Actual Quantum Processor
In this work, we present a Quantum Hopfield Associative Memory (QHAM) and demonstrate its capabilities in simulation and hardware using IBM Quantum Experience.
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.
Towards Improving the Trustworthiness of Hardware based Malware Detector using Online Uncertainty Estimation
Hardware-based Malware Detectors (HMDs) using Machine Learning (ML) models have shown promise in detecting malicious workloads.
A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
In this paper, we consider the problem of learning prediction models for spatiotemporal physical processes driven by unknown partial differential equations (PDEs).
Neural Identification for Control
The proposed method relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law.
Physics-Incorporated Convolutional Recurrent Neural Networks for Source Identification and Forecasting of Dynamical Systems
Spatio-temporal dynamics of physical processes are generally modeled using partial differential equations (PDEs).
MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network
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.
SAFE-DNN: A Deep Neural Network with Spike Assisted Feature Extraction for Noise Robust Inference
We present a Deep Neural Network with Spike Assisted Feature Extraction (SAFE-DNN) to improve robustness of classification under stochastic perturbation of inputs.
ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction
ScieNet integrates unsupervised learning using spiking neural network (SNN) for unsupervised contextual informationextraction with a back-end DNN trained for classification.
Improving Robustness of ReRAM-based Spiking Neural Network Accelerator with Stochastic Spike-timing-dependent-plasticity
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.
Application Inference using Machine Learning based Side Channel Analysis
The proliferation of ubiquitous computing requires energy-efficient as well as secure operation of modern processors.
Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms
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.
HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
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.
Memory Slices: A Modular Building Block for Scalable, Intelligent Memory Systems
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
Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms
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.
NeuroTrainer: An Intelligent Memory Module for Deep Learning Training
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
Cascade Adversarial Machine Learning Regularized with a Unified Embedding
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks.
