arXiv research

Energy savings for DNN inference on resource-constrained devices.

NetFuse merges different DNN models with varying weights for faster inference.

Improved DNN estimator with scalable subsampling for efficient inference.

Low-precision DNNs have been extensively explored in order to reduce the size of DNN models for edge devices. Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision in [5..8]-bits. However, previous studies were limited to studying posit for DNN inference…

Two approaches scale up DNN optimization for diverse edge devices.

The paper explains DNNs by quantifying interactions among input variables.

This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.

Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by operations on the weight matrices describing the DNN. As DNNs incorporate more layers a…

Proposes inference for DNNs in GNRMs, addressing non-independence issues.

Innovative PGMs match neural networks, revealing precise approximations during forward propagation.

Survey connects three DNN generalization fields for better inference.

Framework prevents data leakage in mobile cloud DNNs.

Study uses deep neural networks for causal inference tasks, especially in high-dimensional settings.

Study uses deep neural networks for inference in partially linear models with dependent data.

The weighted nearest neighbors (WNN) estimator has been popularly used as a flexible and easy-to-implement nonparametric tool for mean regression estimation. The bagging technique is an elegant way to form WNN estimators with weights automatically generated to the nearest neighbors; we name the resulting estimator as t…

Uncertainty estimation in deep neural networks is essential for designing reliable and robust AI systems. Applications such as video surveillance for identifying suspicious activities are designed with deep neural networks (DNNs), but DNNs do not provide uncertainty estimates. Capturing reliable uncertainty estimates i…

Paper monitors DNN accuracy to enhance trustworthiness.

Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training methods is not well understood. In this paper, we show that certain Gaussian posterior approximations for Bayesian DNNs are equivalent to GP post…

Paper proposes a new binary quantization method for faster DNN inference.

Pruning improves DNNs against MIA while reducing model size and computation.

Deep learning has delivered its powerfulness in many application domains, especially in image and speech recognition. As the backbone of deep learning, deep neural networks (DNNs) consist of multiple layers of various types with hundreds to thousands of neurons. Embedded platforms are now becoming essential for deep le…

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalability difficulties. The proposed Sparse Deep Neural Network (DNN) Challenge draws upon prior challenges from machine learning, high performanc…

The paper uses deep neural networks to estimate and infer ATE without needing to know the dimension of the data.

Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision ([5..8]-bit). However, majority of studies focus only on DNN inference. In this work, we propose DNN training using posits and compare with the floating point training. We evaluate on both MNIST and F…

State of the art Deep Neural Networks (DNN) can now achieve above human level accuracy on image classification tasks. However their outstanding performances come along with a complex inference mechanism making them arduously interpretable models. In order to understand the underlying prediction rules of DNNs, Dhamdhere…

New method quantifies reliability of neural network image segmentation.

DS-UI improves DNN uncertainty inference by combining a DNN classifier with MoGMM.

Noise injection improves inference privacy in DNN models.

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying priors and approximate posterior distributions over neural network weights. Specifying meaningful weight priors is a challenging problem, particularly for scaling variational inference to deeper architectures involving high dime…

DeepPeep attacks DNN architectures to reveal design details, posing IP theft risks.

IoT nodes compress measurements into DNN outputs for efficient communication.

A new approach for efficient data compression in split DNN computing.

Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms. In this paper, we propose a new method to evaluate DNNs trained with 32bit floating point (float32) accura…

Sparse DNNs face scalability issues; MIT/IEEE/Amazon challenge analyzes best solutions.

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates …

Deep neural networks (DNNs) often require good regularizers to generalize well. Currently, state-of-the-art DNN regularization techniques consist in randomly dropping units and/or connections on each iteration of the training algorithm. Dropout and DropConnect are characteristic examples of such regularizers, that are …

Freezing intermediate layers reduces DNN inference latency.

Hybrid model improves forest growth predictions.

NEMO framework quantizes DNNs for efficient deployment.

Deep neural networks (DNNs) are known as black-box models. In other words, it is difficult to interpret the internal state of the model. Improving the interpretability of DNNs is one of the hot research topics. However, at present, the definition of interpretability for DNNs is vague, and the question of what is a high…

Enhances deep neural networks with fixed-mean Gaussian processes for uncertainty estimation.

TxSim models DNN training on resistive crossbars, improving accuracy and feasibility.

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…

New method learns sparse distributions by thresholding samples, improving performance and efficiency.

Unified framework for accelerating DNNs on resource-limited platforms.

SmartExchange trades memory for computation in neural networks.

Generative model for HW-aware DNN quantization.

With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem. However, without a careful optimization, executing Deep Neural Networks (a key building block of the real-time video stream p…