arXiv subjects

Andreea Danielescu

Publications and source records attributed to Andreea Danielescu.

12 recordsLinked to original sources

arXiv2025

Modeling and Optimizing Performance Bottlenecks for Neuromorphic Accelerators

Neuromorphic accelerators offer promising platforms for machine learning (ML) inference by leveraging event-driven, spatially-expanded architectures that naturally exploit unstructured sparsity through co-located memory and compute. However, their unique architectural characteristics create performance dynamics that differ fundamentally from conventional accelerators. Existing workload optimization approaches for neuromorphic accelerators rely on aggregate network-wide sparsity and operation counting, but the extent to which these metrics actually improve deployed performance remains unknown. This paper presents the first comprehensive performance bound and bottleneck analysis of neuromorphic accelerators, revealing the shortcomings of the conventional metrics and offering an understanding of what facets matter for workload performance. We present both theoretical analytical modeling and extensive empirical characterization of three real neuromorphic accelerators: Brainchip AKD1000, Synsense Speck, and Intel Loihi 2. From these, we establish three distinct accelerator bottleneck states, memory-bound, compute-bound, and traffic-bound, and identify which workload configuration features are likely to exhibit these bottleneck states. We synthesize all of our insights into the floorline performance model, a visual model that identifies performance bounds and informs how to optimize a given workload, based on its position on the model. Finally, we present an optimization methodology that combines sparsity-aware training with floorline-informed partitioning. Our methodology achieves substantial performance improvements at iso-accuracy: up to 3.86x runtime improvement and 3.38x energy reduction compared to prior manually-tuned configurations.

cs.AR↗

arXiv2025

ExoFabric: A Re-moldable Textile System for Creating Customizable Soft Goods and Wearable Applications

Fabric has been a fundamental part of human life for thousands of years, providing comfort, protection, and aesthetic expression. While modern advancements have enhanced fabric's functionality, it remains static and unchangeable, failing to adapt to our evolving body shapes and preferences. This lack of adaptability can lead to unsustainable practices, as consumers often buy more items to meet their changing needs. In this paper, we propose ExoFabric, a re-moldable fabric system for customized soft goods applications. We created ExoFabric by embedding thermoplastic threads into fabric through computerized embroidery to allow for tunability between rigid plastic and conformable fabric. We defined a library of design primitives to enable geometric formability, stiffness, and stretchability by identifying suitable fabrics, threads, embroidery parameters, and machine limitations. To facilitate practical applications, we demonstrated practical methods for linking parameters to application requirements, showcasing form-fitting wearables, structural support, and shape-changeable furniture for repeatable or one-time customization.

cs.ET↗

arXiv2024

Visual Odometry with Neuromorphic Resonator Networks

Visual Odometry (VO) is a method to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements that can accumulate errors, such as inertial sensors or wheel encoders, visual odometry is not compromised by drift. However, image-based VO is computationally demanding, limiting its application in use cases with low-latency, -memory, and -energy requirements. Neuromorphic hardware offers low-power solutions to many vision and AI problems, but designing such solutions is complicated and often has to be assembled from scratch. Here we propose to use Vector Symbolic Architecture (VSA) as an abstraction layer to design algorithms compatible with neuromorphic hardware. Building from a VSA model for scene analysis, described in our companion paper, we present a modular neuromorphic algorithm that achieves state-of-the-art performance on two-dimensional VO tasks. Specifically, the proposed algorithm stores and updates a working memory of the presented visual environment. Based on this working memory, a resonator network estimates the changing location and orientation of the camera. We experimentally validate the neuromorphic VSA-based approach to VO with two benchmarks: one based on an event camera dataset and the other in a dynamic scene with a robotic task.

cs.RO↗

arXiv2024

Neuromorphic Visual Scene Understanding with Resonator Networks

Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference procedure, involving a combinatorial search across object identities and poses. Here we propose a neuromorphic solution exploiting three key concepts: (1) a computational framework based on Vector Symbolic Architectures (VSA) with complex-valued vectors; (2) the design of Hierarchical Resonator Networks (HRN) to factorize the non-commutative transforms translation and rotation in visual scenes; (3) the design of a multi-compartment spiking phasor neuron model for implementing complex-valued resonator networks on neuromorphic hardware. The VSA framework uses vector binding operations to form a generative image model in which binding acts as the equivariant operation for geometric transformations. A scene can, therefore, be described as a sum of vector products, which can then be efficiently factorized by a resonator network to infer objects and their poses. The HRN features a partitioned architecture in which vector binding is equivariant for horizontal and vertical translation within one partition and for rotation and scaling within the other partition. The spiking neuron model allows mapping the resonator network onto efficient and low-power neuromorphic hardware. Our approach is demonstrated on synthetic scenes composed of simple 2D shapes undergoing rigid geometric transformations and color changes. A companion paper demonstrates the same approach in real-world application scenarios for machine vision and robotics.

cs.CV↗

arXiv2023

NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. Prior neuromorphic computing benchmark efforts have not seen widespread adoption due to a lack of inclusive, actionable, and iterative benchmark design and guidelines. To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of researchers across industry and academia, aiming to provide a representative structure for standardizing the evaluation of neuromorphic approaches. The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings. In this article, we outline tasks and guidelines for benchmarks across multiple application domains, and present initial performance baselines across neuromorphic and conventional approaches for both benchmark tracks. NeuroBench is intended to continually expand its benchmarks and features to foster and track the progress made by the research community.

cs.AI↗

arXiv2023

Bioinspired Smooth Neuromorphic Control for Robotic Arms

Beyond providing accurate movements, achieving smooth motion trajectories is a long-standing goal of robotics control theory for arms aiming to replicate natural human movements. Drawing inspiration from biological agents, whose reaching control networks effortlessly give rise to smooth and precise movements, can simplify these control objectives for robot arms. Neuromorphic processors, which mimic the brain's computational principles, are an ideal platform to approximate the accuracy and smoothness of biological controllers while maximizing their energy efficiency and robustness. However, the incompatibility of conventional control methods with neuromorphic hardware limits the computational efficiency and explainability of their existing adaptations. In contrast, the neuronal subnetworks underlying smooth and accurate reaching movements are effective, minimal, and inherently compatible with neuromorphic hardware. In this work, we emulate these networks with a biologically realistic spiking neural network for motor control on neuromorphic hardware. The proposed controller incorporates experimentally-identified short-term synaptic plasticity and specialized neurons that regulate sensory feedback gain to provide smooth and accurate joint control across a wide motion range. Concurrently, it preserves the minimal complexity of its biological counterpart and is directly deployable on Intel's neuromorphic processor. Using the joint controller as a building block and inspired by joint coordination in human arms, we scaled up this approach to control real-world robot arms. The trajectories and smooth, bell-shaped velocity profiles of the resulting motions resembled those of humans, verifying the biological relevance of the controller. Notably, the method achieved state-of-the-art control performance while decreasing the motion jerk by 19% to improve motion smoothness.

cs.RO↗

arXiv2023

Guttation Monitor: Wearable Guttation Sensor for Plant Condition Monitoring and Diagnosis

Plant life plays a critical role in the ecosystem. However, it is difficult for humans to perceive plants' reactions because the biopotential and biochemical responses are invisible to humans. Guttation droplets contain various chemicals which can reflect plant physiology and environmental conditions in real-time. Traditionally, these droplets are collected manually and analyzed in the lab with expensive instruments. Here, we introduce the Guttation Monitor, an on-site and low-cost monitoring technology for guttation droplets. It consists of three parts 1) a paper-based microfluidic chip that can collect guttation droplets and perform colorimetric detection of six chemicals, 2) a self-contained and solar-powered camera module that can capture the result from the chip, and 3) an end-user app that can interpret the result. We discuss this technology's design and implementation, conduct evaluations on tomato plants, conduct interviews, and envision how such a technology could enhance the human-plant relationship in four dimensions.

cs.HC↗

arXiv2022

FlexKeys: Rapidly Customizable 3D Printed Tactile Input Devices with No Assembly Required

Physical input devices serve as a tactile interface between users and computing systems. These devices are often complex assemblies that consist of both electrical and mechanical components making customization difficult and out of reach for non-engineers. While these components can now be 3D printed on demand, they must still be independently designed and assembled. We present FlexKeys, an approach in which devices that include both electrical and deformable components can be created in a single print on a multi-material 3D printer, requiring no assembly. Designers can customize devices including the input type, travel distance and layout of keys, textures of surfaces, and route all electrical signals directly to a microcontroller socket. In many instances, these devices require no support material, producing a functional device the moment a print finishes. We demonstrate this approach by creating a customized keyboard and report on validation measurements of individual input keys as well as highlighting additional designs. This work provides the first step towards lowering the barrier to entry for non-engineers to design custom tactile inputs, enabling occupational and physical therapists, clinicians, and educators to design and create devices directly based on their assessments of individual user needs.

cs.HC↗

arXiv2022

Encoding Event-Based Data With a Hybrid SNN Guided Variational Auto-encoder in Neuromorphic Hardware

Neuromorphic hardware equipped with learning capabilities can adapt to new, real-time data. While models of Spiking Neural Networks (SNNs) can now be trained using gradient descent to reach an accuracy comparable to equivalent conventional neural networks, such learning often relies on external labels. However, real-world data is unlabeled which can make supervised methods inapplicable. To solve this problem, we propose a Hybrid Guided Variational Autoencoder (VAE) which encodes event based data sensed by a Dynamic Vision Sensor (DVS) into a latent space representation using an SNN. These representations can be used as an embedding to measure data similarity and predict labels in real-world data. We show that the Hybrid Guided-VAE achieves 87% classification accuracy on the DVSGesture dataset and it can encode the sparse, noisy inputs into an interpretable latent space representation, visualized through T-SNE plots. We also implement the encoder component of the model on neuromorphic hardware and discuss the potential for our algorithm to enable real-time learning from real-world event data.

cs.NE↗

arXiv2022

Iterative Design of Gestures During Elicitation: Understanding the Role of Increased Production

Previous gesture elicitation studies have found that user proposals are influenced by legacy bias which may inhibit users from proposing gestures that are most appropriate for an interaction. Increasing production during elicitation studies has shown promise moving users beyond legacy gestures. However, variety decreases as more symbols are produced. While several studies have used increased production since its introduction, little research has focused on understanding the effect on the proposed gesture quality, on why variety decreases, and on whether increased production should be limited. In this paper, we present a gesture elicitation study aimed at understanding the impact of increased production. We show that users refine the most promising gestures and that how long it takes to find promising gestures varies by participant. We also show that gestural refinements provide insight into the gestural features that matter for users to assign semantic meaning and discuss implications for training gesture classifiers.

cs.HC↗

arXiv2021

OnTarget: An Electronic Archery Scoring

There are several challenges in creating an electronic archery scoring system using computer vision techniques. Variability of light, reconstruction of the target from several images, variability of target configuration, and filtering noise were significant challenges during the creation of this scoring system. This paper discusses the approach used to determine where an arrow hits a target, for any possible single or set of targets and provides an algorithm that balances the difficulty of robust arrow detection while retaining the required accuracy.

cs.CV↗

arXiv2020

End-to-End Auditory Object Recognition via Inception Nucleus

Machine learning approaches to auditory object recognition are traditionally based on engineered features such as those derived from the spectrum or cepstrum. More recently, end-to-end classification systems in image and auditory recognition systems have been developed to learn features jointly with classification and result in improved classification accuracy. In this paper, we propose a novel end-to-end deep neural network to map the raw waveform inputs to sound class labels. Our network includes an "inception nucleus" that optimizes the size of convolutional filters on the fly that results in reducing engineering efforts dramatically. Classification results compared favorably against current state-of-the-art approaches, besting them by 10.4 percentage points on the Urbansound8k dataset. Analyses of learned representations revealed that filters in the earlier hidden layers learned wavelet-like transforms to extract features that were informative for classification.

cs.SD↗