Search Results for author:
Found 18 papers, 8 papers with code
This Probably Looks Exactly Like That: An Invertible Prototypical Network
We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning.
Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness
We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models.
How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?
Surging interest in deep learning from high-stakes domains has precipitated concern over the inscrutable nature of black box neural networks.
Pixel-Grounded Prototypical Part Networks
Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning.
HomOpt: A Homotopy-Based Hyperparameter Optimization Method
Traditional methods, like grid search and Bayesian optimization, often struggle to quickly adapt and efficiently search the loss landscape.
Unfooling Perturbation-Based Post Hoc Explainers
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.
Motif Mining: Finding and Summarizing Remixed Image Content
On the internet, images are no longer static; they have become dynamic content.
Learning Interpretable Models Through Multi-Objective Neural Architecture Search
Monumental advances in deep learning have led to unprecedented achievements across various domains.
Explainable Artificial Intelligence (XAI)
Image Classification
+1
A Framework for Evaluating Post Hoc Feature-Additive Explainers
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.
Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems
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.
SIRNet: Understanding Social Distancing Measures with Hybrid Neural Network Model for COVID-19 Infectious Spread
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
Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge
Additionally, the framework is amenable for different quantization approaches and supports mixed-precision floating point and fixed-point numerical formats.
Deep Learning Training on the Edge with Low-Precision Posits
Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision ([5.. 8]-bit).
Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting
Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry.
Performance-Efficiency Trade-off of Low-Precision Numerical Formats in Deep Neural Networks
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.
Deep Positron: A Deep Neural Network Using the Posit Number System
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.
PositNN: Tapered Precision Deep Learning Inference for the Edge
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.
Mod-DeepESN: Modular Deep Echo State Network
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices.
