scholarly journals Does spatial invariance result from insensitivity to change?

2016 ◽  
Vol 7 (14) ◽  
pp. 11 ◽  
Author(s):  
Frederick A. A. Kingdom ◽  
David J. Field ◽  
Adriana Olmos
Keyword(s):  
Spatial Invariance

Detecting Scene-Plausible Perceptible Backdoors in Trained DNNs without Access to the Training Set

2021 ◽  
pp. 1-43
Author(s):  
Zhen Xiang ◽  
David J. Miller ◽  
Hang Wang ◽  
George Kesidis
Keyword(s):  
Cell Phone ◽  
Test Sample ◽  
Training Set ◽  
Target Class ◽  
Trained Classifier ◽  
Training Samples ◽  
Spatial Invariance

Backdoor data poisoning attacks add mislabeled examples to the training set, with an embedded backdoor pattern, so that the classifier learns to classify to a target class whenever the backdoor pattern is present in a test sample. Here, we address posttraining detection of scene-plausible perceptible backdoors, a type of backdoor attack that can be relatively easily fashioned, particularly against DNN image classifiers. A posttraining defender does not have access to the potentially poisoned training set, only to the trained classifier, as well as some unpoisoned examples that need not be training samples. Without the poisoned training set, the only information about a backdoor pattern is encoded in the DNN's trained weights. This detection scenario is of great import considering legacy and proprietary systems, cell phone apps, as well as training outsourcing, where the user of the classifier will not have access to the entire training set. We identify two important properties of scene-plausible perceptible backdoor patterns, spatial invariance and robustness, based on which we propose a novel detector using the maximum achievable misclassification fraction (MAMF) statistic. We detect whether the trained DNN has been backdoor-attacked and infer the source and target classes. Our detector outperforms existing detectors and, coupled with an imperceptible backdoor detector, helps achieve posttraining detection of most evasive backdoors of interest.

Optimal Control of Arrays of Microcantilevers

1999 ◽  
Vol 121 (4) ◽  
pp. 686-690 ◽  
Author(s):  
Mariateresa Napoli ◽  
Bassam Bamieh ◽  
Mohammed Dahleh
Keyword(s):  
Optimal Control ◽  
Atomic Force Microscopy ◽  
Optimal Controller ◽  
Invariant System ◽  
Sensors And Actuators ◽  
Force Microscopy ◽  
Atomic Force ◽  
Distributed Array ◽  
Spatial Invariance ◽  
Analytic Expression

In this paper we will present a model for an array of microcantilevers that are used in Atomic Force Microscopy and nano-scale manufacturing. The microcantilevers are connected to each other through a common base, and are individually actuated. The sensors are also integrated on each microcantilever. We consider the problem of controlling a tightly packed array of identical microcantilevers that are dynamically coupled. This system is an example of a spatially-invariant system with a distributed array of sensors and actuators. We exploit the spatial invariance of the problem to design optimal ℋ2 controllers for this array. An analytic expression for the optimal controller is derived in the transformed domain, and estimates of the coupling range of the controller is obtained.

scholarly journals Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking

2020 ◽  
Vol 34 (04) ◽  
pp. 3684-3692
Author(s):  
Eric Crawford ◽  
Joelle Pineau
Keyword(s):  
Object Tracking ◽  
Spatial Attention ◽  
Intelligent Agent ◽  
Current Work ◽  
Visual World ◽  
Reasoning Process ◽  
Series Of Experiments ◽  
Spatial Invariance ◽  
Tracking Objects ◽  
Object Level

The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects without supervision (i.e. without access to annotated training videos) since this will allow agents to begin operating in new environments with minimal human assistance. The task of learning to discover and track objects in videos, which we call unsupervised object tracking, has grown in prominence in recent years; however, most architectures that address it still struggle to deal with large scenes containing many objects. In the current work, we propose an architecture that scales well to the large-scene, many-object setting by employing spatially invariant computations (convolutions and spatial attention) and representations (a spatially local object specification scheme). In a series of experiments, we demonstrate a number of attractive features of our architecture; most notably, that it outperforms competing methods at tracking objects in cluttered scenes with many objects, and that it can generalize well to videos that are larger and/or contain more objects than videos encountered during training.

Spatial invariance in anticipatory orienting behaviour during human navigation

2003 ◽  
Vol 339 (3) ◽  
pp. 243-247 ◽  
Author(s):  
Pascal Prévost ◽  
Ivanenko Yuri ◽  
Grasso Renato ◽  
Berthoz Alain
Keyword(s):  
Human Navigation ◽  
Spatial Invariance

scholarly journals Deep-seismic-prior-based reconstruction of seismic data using convolutional neural networks

Geophysics ◽  
2020 ◽  
pp. 1-93
Author(s):  
Liuqun Liu ◽  
Lihua Fu ◽  
Meng Zhang
Keyword(s):  
Deep Learning ◽  
Seismic Data ◽  
Singular Spectrum Analysis ◽  
Reconstruction Methods ◽  
Reconstruction Performance ◽  
Network Output ◽  
Novel Method ◽  
Spatial Invariance ◽  
Seismic Data Reconstruction ◽  
Structure Choice

The reconstruction of seismic data with missing traces has been a long-standing issue in seismic data processing; deep learning methods have attracted significant attention in seismic data reconstruction. One barrier associated with these deep-learning based reconstruction methods is the need for large training datasets, which are difficult to acquire owing to physical or financial constraints in practice. A novel method for the recovery of incomplete seismic data without the need of training datasets was developed. Seismic prior is implicitly captured based on the particular CNN structure choice, referred to as the “deep-seismic-prior-based”. The learned network weights are the parameters that represent seismic data, and as the convolutional filter weights are shared for spatial invariance, the CNN structure can function as a regularizer to guide the network learning. The reconstruction is realized during the iterative process by minimizing the mean square error (MSE) between the network output and the original corrupted seismic data. Our method could handle both irregular and regular seismic data, and testing its performance using both synthetic and field data showed it was more advantageous compared with the singular spectrum analysis (SSA) and de-aliased Cadzow methods employed in the reconstruction of irregular and regular data, respectively. The experimental results showed that the proposed method provided better reconstruction performance than the SSA and Cadzow methods.

Sign in / Sign up

Export Citation Format

Share Document