Related papers: Analog Optical Inference on Million-Record Mortgag…
The accuracy of camera-based object detection (CBOD) built upon deep learning is often evaluated against the real objects in frames only. However, such simplistic evaluation ignores the fact that many unimportant objects are small, distant,…
In this work we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner. Our comparison uses pareto fronts based on randomly sampled…
Multifocal plane microscopy (MUM) allows three dimensional objects to be imaged in a single camera frame. Our approach uses dual orthogonal diffraction phase gratings with a quadratic distortion of the lines to apply defocus to the first…
Previous work shows that humans tend to prefer large bounding boxes over small bounding boxes with the same IoU. However, we show here that commonly used object detectors predict large and small boxes equally often. In this work, we…
Amortized Bayesian model comparison (BMC) enables fast probabilistic ranking of models via simulation-based training of neural surrogates. However, the accuracy of neural surrogates deteriorates when simulation models are misspecified; the…
Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI…
In a growing number of applications, there is a need to digitize signals whose spectral characteristics are challenging for traditional Analog-to-Digital Converters (ADCs). Examples, among others, include systems where the ADC must acquire…
Images captured through smartphone cameras often suffer from degradation, blur being one of the major ones, posing a challenge in processing these images for downstream tasks. In this paper we propose low-compute lightweight patch-wise…
AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that…
Recent advances in artificial intelligence, coupled with increasing data bandwidth requirements, in applications such as video processing and high-resolution sensing, have created a growing demand for high computational performance under…
Standard risk models reduce the rich dependence structure of financial markets to scalar volatility estimates, discarding the topological information encoded in cross-asset correlation networks. We present ORCA (Online Regime Correlation…
Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…
During the past decade, implementing reconstruction algorithms on hardware has been at the center of much attention in the field of real-time reconstruction in Compressed Sensing (CS). Orthogonal Matching Pursuit (OMP) is the most widely…
Convolutional Neural Networks (CNN) have had a huge success in many areas of computer vision and medical image analysis. However, there is still an immense potential for performance improvement in mammogram breast cancer detection…
Bias-scalable analog computing is attractive for implementing machine learning (ML) processors with distinct power-performance specifications. For instance, ML implementations for server workloads are focused on higher computational…
Accurate extrinsic calibration between LiDAR and camera sensors is important for reliable perception in autonomous systems. In this paper, we present a novel multi-objective optimization framework that jointly minimizes the geometric…
Artificial intelligence is widely used in everyday life. However, an insufficient computing efficiency due to the so-called von Neumann bottleneck cannot satisfy the demand for real-time processing of rapidly growing data. Memristive…
Objective: The advent of Electronic Medical Records (EMR) with large electronic imaging databases along with advances in deep neural networks with machine learning has provided a unique opportunity to achieve milestones in automated image…
Diffraction limited resolution adaptive optics (AO) correction in visible wavelengths requires a high performance control. In this paper we investigate infinite impulse response filters that optimize the wavefront correction: we tested…
We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model, informed by work on neural scaling laws, and infer a decomposition of progress into the…