arXiv subjects

Kaushik Roy

Publications and source records attributed to Kaushik Roy.

At least 199 records · Page 11Linked to original sources

arXiv2021

Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures

Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to perceive scene accurately when the dynamic range is high. Event-based cameras, on the other hand, overcome these limitations by asynchronously detecting the variation in individual pixel intensities. However, event cameras only provide information about pixels in motion, leading to sparse data. Hence, estimating the overall dense behavior of pixels is difficult. To address such issues associated with the sensors, we present Fusion-FlowNet, a sensor fusion framework for energy-efficient optical flow estimation using both frame- and event-based sensors, leveraging their complementary characteristics. Our proposed network architecture is also a fusion of Spiking Neural Networks (SNNs) and Analog Neural Networks (ANNs) where each network is designed to simultaneously process asynchronous event streams and regular frame-based images, respectively. Our network is end-to-end trained using unsupervised learning to avoid expensive video annotations. The method generalizes well across distinct environments (rapid motion and challenging lighting conditions) and demonstrates state-of-the-art optical flow prediction on the Multi-Vehicle Stereo Event Camera (MVSEC) dataset. Furthermore, our network offers substantial savings in terms of the number of network parameters and computational energy cost.

cs.CV↗

arXiv2021

Gradient Projection Memory for Continual Learning

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance based weight update or replay of old data from the memory. In contrast, we propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for the past tasks. We find the bases of these subspaces by analyzing network representations (activations) after learning each task with Singular Value Decomposition (SVD) in a single shot manner and store them in the memory as Gradient Projection Memory (GPM). With qualitative and quantitative analyses, we show that such orthogonal gradient descent induces minimum to no interference with the past tasks, thereby mitigates forgetting. We evaluate our algorithm on diverse image classification datasets with short and long sequences of tasks and report better or on-par performance compared to the state-of-the-art approaches.

cs.LG↗

arXiv2021

On the Intrinsic Robustness of NVM Crossbars Against Adversarial Attacks

The increasing computational demand of Deep Learning has propelled research in special-purpose inference accelerators based on emerging non-volatile memory (NVM) technologies. Such NVM crossbars promise fast and energy-efficient in-situ Matrix Vector Multiplication (MVM) thus alleviating the long-standing von Neuman bottleneck in today's digital hardware. However, the analog nature of computing in these crossbars is inherently approximate and results in deviations from ideal output values, which reduces the overall performance of Deep Neural Networks (DNNs) under normal circumstances. In this paper, we study the impact of these non-idealities under adversarial circumstances. We show that the non-ideal behavior of analog computing lowers the effectiveness of adversarial attacks, in both Black-Box and White-Box attack scenarios. In a non-adaptive attack, where the attacker is unaware of the analog hardware, we observe that analog computing offers a varying degree of intrinsic robustness, with a peak adversarial accuracy improvement of 35.34%, 22.69%, and 9.90% for white box PGD (epsilon=1/255, iter=30) for CIFAR-10, CIFAR-100, and ImageNet respectively. We also demonstrate "Hardware-in-Loop" adaptive attacks that circumvent this robustness by utilizing the knowledge of the NVM model.

cs.ET↗

arXiv2021

Knowledge Infused Policy Gradients for Adaptive Pandemic Control

COVID-19 has impacted nations differently based on their policy implementations. The effective policy requires taking into account public information and adaptability to new knowledge. Epidemiological models built to understand COVID-19 seldom provide the policymaker with the capability for adaptive pandemic control (APC). Among the core challenges to be overcome include (a) inability to handle a high degree of non-homogeneity in different contributing features across the pandemic timeline, (b) lack of an approach that enables adaptive incorporation of public health expert knowledge, and (c) transparent models that enable understanding of the decision-making process in suggesting policy. In this work, we take the early steps to address these challenges using Knowledge Infused Policy Gradient (KIPG) methods. Prior work on knowledge infusion does not handle soft and hard imposition of varying forms of knowledge in disease information and guidelines to necessarily comply with. Furthermore, the models do not attend to non-homogeneity in feature counts, manifesting as partial observability in informing the policy. Additionally, interpretable structures are extracted post-learning instead of learning an interpretable model required for APC. To this end, we introduce a mathematical framework for KIPG methods that can (a) induce relevant feature counts over multi-relational features of the world, (b) handle latent non-homogeneous counts as hidden variables that are linear combinations of kernelized aggregates over the features, and (b) infuse knowledge as functional constraints in a principled manner. The study establishes a theory for imposing hard and soft constraints and simulates it through experiments. In comparison with knowledge-intensive baselines, we show quick sample efficient adaptation to new knowledge and interpretability in the learned policy, especially in a pandemic context.

cs.AI↗

arXiv2021

SPACE: Structured Compression and Sharing of Representational Space for Continual Learning

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'. Efforts to overcome this phenomenon often utilize resources poorly, for instance, by growing the network architecture or needing to save parametric importance scores, or violate data privacy between tasks. To tackle this, we propose SPACE, an algorithm that enables a network to learn continually and efficiently by partitioning the learnt space into a Core space, that serves as the condensed knowledge base over previously learned tasks, and a Residual space, which is akin to a scratch space for learning the current task. After learning each task, the Residual is analyzed for redundancy, both within itself and with the learnt Core space. A minimal number of extra dimensions required to explain the current task are added to the Core space and the remaining Residual is freed up for learning the next task. We evaluate our algorithm on P-MNIST, CIFAR and a sequence of 8 different datasets, and achieve comparable accuracy to the state-of-the-art methods while overcoming catastrophic forgetting. Additionally, our algorithm is well suited for practical use. The partitioning algorithm analyzes all layers in one shot, ensuring scalability to deeper networks. Moreover, the analysis of dimensions translates to filter-level sparsity, and the structured nature of the resulting architecture gives us up to 5x improvement in energy efficiency during task inference over the current state-of-the-art.

cs.LG↗

arXiv2021

"Is depression related to cannabis?": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision

With strong marketing advocacy of the benefits of cannabis use for improved mental health, cannabis legalization is a priority among legislators. However, preliminary scientific research does not conclusively associate cannabis with improved mental health. In this study, we explore the relationship between depression and consumption of cannabis in a targeted social media corpus involving personal use of cannabis with the intent to derive its potential mental health benefit. We use tweets that contain an association among three categories annotated by domain experts - Reason, Effect, and Addiction. The state-of-the-art Natural Langauge Processing techniques fall short in extracting these relationships between cannabis phrases and the depression indicators. We seek to address the limitation by using domain knowledge; specifically, the Drug Abuse Ontology for addiction augmented with Diagnostic and Statistical Manual of Mental Disorders lexicons for mental health. Because of the lack of annotations due to the limited availability of the domain experts' time, we use supervised contrastive learning in conjunction with GPT-3 trained on a vast corpus to achieve improved performance even with limited supervision. Experimental results show that our method can significantly extract cannabis-depression relationships better than the state-of-the-art relation extractor. High-quality annotations can be provided using a nearest neighbor approach using the learned representations that can be used by the scientific community to understand the association between cannabis and depression better.

cs.CL↗

arXiv2020

Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection

Deep neural networks have found widespread adoption in solving complex tasks ranging from image recognition to natural language processing. However, these networks make confident mispredictions when presented with data that does not belong to the training distribution, i.e. out-of-distribution (OoD) samples. In this paper we explore whether the property of Vicinal Risk Minimization (VRM) to smoothly interpolate between different class boundaries helps to train better OoD detectors. We apply VRM to existing OoD detection techniques and show their improved performance. We observe that existing OoD detectors have significant memory and compute overhead, hence we leverage VRM to develop an OoD detector with minimal overheard. Our detection method introduces an auxiliary class for classifying OoD samples. We utilize mixup in two ways to implement Vicinal Risk Minimization. First, we perform mixup within the same class and second, we perform mixup with Gaussian noise when training the auxiliary class. Our method achieves near competitive performance with significantly less compute and memory overhead when compared to existing OoD detection techniques. This facilitates the deployment of OoD detection on edge devices and expands our understanding of Vicinal Risk Minimization for use in training OoD detectors.

cs.LG↗

arXiv2020

DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks

Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold for each layer of the SNN are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The analog pixel values of an image are directly applied to the input layer of DIET-SNN without the need to convert to spike-train. The first convolutional layer is trained to convert inputs into spikes where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and dense layers of the network. The reduced latency combined with high activation sparsity provides large improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with 5 timesteps (inference latency) on the ImageNet dataset with 12x less compute energy than an equivalent standard ANN. Additionally, DIET-SNN performs 20-500x faster inference compared to other state-of-the-art SNN models.

cs.NE↗

arXiv2020

COVID-19 in Spain and India: Comparing Policy Implications by Analyzing Epidemiological and Social Media Data

The COVID-19 pandemic has forced public health experts to develop contingent policies to stem the spread of infection, including measures such as partial/complete lockdowns. The effectiveness of these policies has varied with geography, population distribution, and effectiveness in implementation. Consequently, some nations (e.g., Taiwan, Haiti) have been more successful than others (e.g., United States) in curbing the outbreak. A data-driven investigation into effective public health policies of a country would allow public health experts in other nations to decide future courses of action to control the outbreaks of disease and epidemics. We chose Spain and India to present our analysis on regions that were similar in terms of certain factors: (1) population density, (2) unemployment rate, (3) tourism, and (4) quality of living. We posit that citizen ideology obtainable from twitter conversations can provide insights into conformity to policy and suitably reflect on future case predictions. A milestone when the curves show the number of new cases diverging from each other is used to define a time period to extract policy-related tweets while the concepts from a causality network of policy-dependent sub-events are used to generate concept clouds. The number of new cases is predicted using sentiment scores in a regression model. We see that the new case predictions reflects twitter sentiment, meaningfully tied to a trigger sub-event that enables policy-related findings for Spain and India to be effectively compared.

cs.SI↗

arXiv2020

DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks

Spiking Neural Networks (SNNs) offer a promising alternative to traditional deep learning frameworks, since they provide higher computational efficiency due to event-driven information processing. SNNs distribute the analog values of pixel intensities into binary spikes over time. However, the most widely used input coding schemes, such as Poisson based rate-coding, do not leverage the additional temporal learning capability of SNNs effectively. Moreover, these SNNs suffer from high inference latency which is a major bottleneck to their deployment. To overcome this, we propose a scalable time-based encoding scheme that utilizes the Discrete Cosine Transform (DCT) to reduce the number of timesteps required for inference. DCT decomposes an image into a weighted sum of sinusoidal basis images. At each time step, the Hadamard product of the DCT coefficients and a single frequency base, taken in order, is given to an accumulator that generates spikes upon crossing a threshold. We use the proposed scheme to learn DCT-SNN, a low-latency deep SNN with leaky-integrate-and-fire neurons, trained using surrogate gradient descent based backpropagation. We achieve top-1 accuracy of 89.94%, 68.3% and 52.43% on CIFAR-10, CIFAR-100 and TinyImageNet, respectively using VGG architectures. Notably, DCT-SNN performs inference with 2-14X reduced latency compared to other state-of-the-art SNNs, while achieving comparable accuracy to their standard deep learning counterparts. The dimension of the transform allows us to control the number of timesteps required for inference. Additionally, we can trade-off accuracy with latency in a principled manner by dropping the highest frequency components during inference.

cs.LG↗

arXiv2020

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based cameras suffer critically. This is attributed to their high temporal resolution, high dynamic range, and low-power consumption. However, conventional computer vision methods as well as deep Analog Neural Networks (ANNs) are not suited to work well with the asynchronous and discrete nature of event camera outputs. Spiking Neural Networks (SNNs) serve as ideal paradigms to handle event camera outputs, but deep SNNs suffer in terms of performance due to the spike vanishing phenomenon. To overcome these issues, we present Spike-FlowNet, a deep hybrid neural network architecture integrating SNNs and ANNs for efficiently estimating optical flow from sparse event camera outputs without sacrificing the performance. The network is end-to-end trained with self-supervised learning on Multi-Vehicle Stereo Event Camera (MVSEC) dataset. Spike-FlowNet outperforms its corresponding ANN-based method in terms of the optical flow prediction capability while providing significant computational efficiency.

cs.NE↗

arXiv2020

Inclusive prompt photon-jet correlations as a probe of gluon saturation in electron-nucleus scattering at small $x$

We compute the differential cross-section for inclusive prompt photon$+$quark production in deeply inelastic scattering of electrons off nuclei at small $x$ ($e+A$ DIS) in the framework of the Color Glass Condensate effective field theory. The result is expressed as a convolution of the leading order (in the strong coupling $α_{\mathrm{s}}$) impact factor for the process and universal dipole matrix elements, in the limit of hard photon transverse momentum relative to the nuclear saturation scale $Q_{s,A}(x)$. We perform a numerical study of this process for the kinematics of the Electron-Ion Collider (EIC), exploring in particular the azimuthal angle correlations between the final state photon and quark. We observe a systematic suppression and broadening pattern of the back-to-back peak in the relative azimuthal angle distribution, as the saturation scale is increased by replacing proton targets with gold nuclei. Our results suggest that photon+jet final states in inclusive $e+A$ DIS at high energies are in general a promising channel for exploring gluon saturation that is complementary to inclusive and diffractive dijet production. They also provide a sensitive empirical test of the universality of dipole matrix elements when compared to identical measurements in proton-nucleus collisions. However because photon+jet correlations at small $x$ in EIC kinematics require jet reconstruction at small $k_\perp$, it will be important to study their feasibility relative to photon-hadron correlations.

hep-ph↗

arXiv2020

Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations

In the recent quest for trustworthy neural networks, we present Spiking Neural Network (SNN) as a potential candidate for inherent robustness against adversarial attacks. In this work, we demonstrate that adversarial accuracy of SNNs under gradient-based attacks is higher than their non-spiking counterparts for CIFAR datasets on deep VGG and ResNet architectures, particularly in blackbox attack scenario. We attribute this robustness to two fundamental characteristics of SNNs and analyze their effects. First, we exhibit that input discretization introduced by the Poisson encoder improves adversarial robustness with reduced number of timesteps. Second, we quantify the amount of adversarial accuracy with increased leak rate in Leaky-Integrate-Fire (LIF) neurons. Our results suggest that SNNs trained with LIF neurons and smaller number of timesteps are more robust than the ones with IF (Integrate-Fire) neurons and larger number of timesteps. Also we overcome the bottleneck of creating gradient-based adversarial inputs in temporal domain by proposing a technique for crafting attacks from SNN

cs.CV↗

arXiv2020

Towards Understanding the Effect of Leak in Spiking Neural Networks

Spiking Neural Networks (SNNs) are being explored to emulate the astounding capabilities of human brain that can learn and compute functions robustly and efficiently with noisy spiking activities. A variety of spiking neuron models have been proposed to resemble biological neuronal functionalities. With varying levels of bio-fidelity, these models often contain a leak path in their internal states, called membrane potentials. While the leaky models have been argued as more bioplausible, a comparative analysis between models with and without leak from a purely computational point of view demands attention. In this paper, we investigate the questions regarding the justification of leak and the pros and cons of using leaky behavior. Our experimental results reveal that leaky neuron model provides improved robustness and better generalization compared to models with no leak. However, leak decreases the sparsity of computation contrary to the common notion. Through a frequency domain analysis, we demonstrate the effect of leak in eliminating the high-frequency components from the input, thus enabling SNNs to be more robust against noisy spike-inputs.

cs.NE↗

arXiv2020

Fitted Q-Learning for Relational Domains

We consider the problem of Approximate Dynamic Programming in relational domains. Inspired by the success of fitted Q-learning methods in propositional settings, we develop the first relational fitted Q-learning algorithms by representing the value function and Bellman residuals. When we fit the Q-functions, we show how the two steps of Bellman operator; application and projection steps can be performed using a gradient-boosting technique. Our proposed framework performs reasonably well on standard domains without using domain models and using fewer training trajectories.

cs.LG↗

arXiv2020

RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbars

Resistive crossbars designed with non-volatile memory devices have emerged as promising building blocks for Deep Neural Network (DNN) hardware, due to their ability to compactly and efficiently realize vector-matrix multiplication (VMM), the dominant computational kernel in DNNs. However, a key challenge with resistive crossbars is that they suffer from a range of device and circuit level non-idealities such as interconnect parasitics, peripheral circuits, sneak paths, and process variations. These non-idealities can lead to errors in VMMs, eventually degrading the DNN's accuracy. It is therefore critical to study the impact of crossbar non-idealities on the accuracy of large-scale DNNs. However, this is challenging because existing device and circuit models are too slow to use in application-level evaluations. We present RxNN, a fast and accurate simulation framework to evaluate large-scale DNNs on resistive crossbar systems. RxNN splits and maps the computations involved in each DNN layer into crossbar operations, and evaluates them using a Fast Crossbar Model (FCM) that accurately captures the errors arising due to crossbar non-idealities while being four-to-five orders of magnitude faster than circuit simulation. FCM models a crossbar-based VMM operation using three stages - non-linear models for the input and output peripheral circuits (DACs and ADCs), and an equivalent non-ideal conductance matrix for the core crossbar array. We implement RxNN by extending the Caffe machine learning framework and use it to evaluate a suite of six large-scale DNNs developed for the ImageNet Challenge. Our experiments reveal that resistive crossbar non-idealities can lead to significant accuracy degradations (9.6%-32%) for these large-scale DNNs. To the best of our knowledge, this work is the first quantitative evaluation of the accuracy of large-scale DNNs on resistive crossbar based hardware.

cs.ET↗

arXiv2020

Conditionally Deep Hybrid Neural Networks Across Edge and Cloud

The pervasiveness of "Internet-of-Things" in our daily life has led to a recent surge in fog computing, encompassing a collaboration of cloud computing and edge intelligence. To that effect, deep learning has been a major driving force towards enabling such intelligent systems. However, growing model sizes in deep learning pose a significant challenge towards deployment in resource-constrained edge devices. Moreover, in a distributed intelligence environment, efficient workload distribution is necessary between edge and cloud systems. To address these challenges, we propose a conditionally deep hybrid neural network for enabling AI-based fog computing. The proposed network can be deployed in a distributed manner, consisting of quantized layers and early exits at the edge and full-precision layers on the cloud. During inference, if an early exit has high confidence in the classification results, it would allow samples to exit at the edge, and the deeper layers on the cloud are activated conditionally, which can lead to improved energy efficiency and inference latency. We perform an extensive design space exploration with the goal of minimizing energy consumption at the edge while achieving state-of-the-art classification accuracies on image classification tasks. We show that with binarized layers at the edge, the proposed conditional hybrid network can process 65% of inferences at the edge, leading to 5.5x computational energy reduction with minimal accuracy degradation on CIFAR-10 dataset. For the more complex dataset CIFAR-100, we observe that the proposed network with 4-bit quantization at the edge achieves 52% early classification at the edge with 4.8x energy reduction. The analysis gives us insights on designing efficient hybrid networks which achieve significantly higher energy efficiency than full-precision networks for edge-cloud based distributed intelligence systems.

cs.LG↗

arXiv2020

Probing Nucleons and Nuclei in High Energy Collisions

This volume is a collection of contributions for the 7-week program "Probing Nucleons and Nuclei in High Energy Collisions" that was held at the Institute for Nuclear Theory in Seattle, WA, USA, from October 1 until November 16, 2018. The program was dedicated to the physics of the Electron Ion Collider (EIC), the world's first polarized electron-nucleon (ep) and electron-nucleus (eA) collider to be constructed in the USA. These proceedings are organized by chapters, corresponding to the weeks of the program: Week I, Generalized parton distributions; Week II, Transverse spin and TMDs; Week III, Longitudinal spin; Week IV, Symposium week; Weeks V & VI, eA collisions; Week VII, pA and AA collisions. We hope these proceedings will be useful to readers as a compilation of EIC-related science at the end of the second decade of the XXI century.

hep-ph↗