no code implementations • 28 Oct 2023 • Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Zachariah Carmichael, Vineet Gundecha, Sahand Ghorbanpour, Ricardo Luna, Gutierrez Antonio Guillen, Avisek Naug
We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models.
Surging interest in deep learning from high-stakes domains has precipitated concern over the inscrutable nature of black box neural networks.
Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning.
Traditional methods, like grid search and Bayesian optimization, often struggle to quickly adapt and efficiently search the loss landscape.
We propose algorithms for the detection (CAD-Detect) and defense (CAD-Defend) of these attacks, which are aided by our novel conditional anomaly detection approach, KNN-CAD.
On the internet, images are no longer static; they have become dynamic content.
Monumental advances in deep learning have led to unprecedented achievements across various domains.
In this work, we propose a framework for the evaluation of post hoc explainers on ground truth that is directly derived from the additive structure of a model.
Computer vision approaches are widely used by autonomous robotic systems to sense the world around them and to guide their decision making as they perform diverse tasks such as collision avoidance, search and rescue, and object manipulation.
The SARS-CoV-2 infectious outbreak has rapidly spread across the globe and precipitated varying policies to effectuate physical distancing to ameliorate its impact.
Populations and Evolution
Additionally, the framework is amenable for different quantization approaches and supports mixed-precision floating point and fixed-point numerical formats.
Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision ([5.. 8]-bit).
Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry.
Our results indicate that posits are a natural fit for DNN inference, outperforming at $\leq$8-bit precision, and can be realized with competitive resource requirements relative to those of floating point.
We propose a precision-adaptable FPGA soft core for exact multiply-and-accumulate for uniform comparison across three numerical formats, fixed, floating-point and posit.
Conventional reduced-precision numerical formats, such as fixed-point and floating point, cannot accurately represent deep neural network parameters with a nonlinear distribution and small dynamic range.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices.