Search Results for author:
Found 13 papers, 0 papers with code
Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning
We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks.
Conformalized Multimodal Uncertainty Regression and Reasoning
This paper introduces a lightweight uncertainty estimator capable of predicting multimodal (disjoint) uncertainty bounds by integrating conformal prediction with a deep-learning regressor.
Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge
In the expanding landscape of AI-enabled robotics, robust quantification of predictive uncertainties is of great importance.
ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation
Moreover, our novel array micro-architecture enables adaptive stitching of cells column-wise and row-wise, thereby facilitating perfect parallelism in computations.
Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning
Specifically, our work capitalizes on the inference mechanism of the recurrent attention model (RAM), where only a small window of input domain (glimpse) is processed in a one time step, and the outputs from multiple glimpses are combined through a hidden vector to determine the overall classification output of the problem.
Memory-Immersed Collaborative Digitization for Area-Efficient Compute-in-Memory Deep Learning
We discuss various networking configurations among CiM arrays where Flash, SA, and their hybrid digitization steps can be efficiently implemented using the proposed memory-immersed scheme.
Lightweight, Uncertainty-Aware Conformalized Visual Odometry
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments.
MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence
Using Bayesian inference, not only the prediction itself, but the prediction confidence can also be extracted for planning risk-aware actions.
ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators
Our proposed ENOS framework allows an optimal layer-wise integration of inference operators and computing modes to achieve the desired balance of energy and accuracy.
Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays
Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3D map representation using a harmonic mean of "Gaussian-like" mixture (HMGM) model.
Indoor Localization
Robotics
Hardware Architecture
Image and Video Processing
B.7; I.2.9
Low Latency CMOS Hardware Acceleration for Fully Connected Layers in Deep Neural Networks
We present a novel low latency CMOS hardware accelerator for fully connected (FC) layers in deep neural networks (DNNs).
$MC^2RAM$: Markov Chain Monte Carlo Sampling in SRAM for Fast Bayesian Inference
This work discusses the implementation of Markov Chain Monte Carlo (MCMC) sampling from an arbitrary Gaussian mixture model (GMM) within SRAM.
Supported-BinaryNet: Bitcell Array-based Weight Supports for Dynamic Accuracy-Latency Trade-offs in SRAM-based Binarized Neural Network
To reduce the power overheads, we propose a dynamic drop out a part of the support parameters.
