scholarly journals Temporal contiguity training does not affect size-tolerant representations in object-selective cortex

2019 ◽  
Author(s):  
Chayenne Van Meel ◽  
Hans P. Op de Beeck
Keyword(s):  
Human Visual System ◽  
Temporal Contiguity ◽  
Training Phase ◽  
Object Identity ◽  
Prior Work ◽  
Training Process ◽  
Size Change ◽  
Bold Responses ◽  
Human Object ◽  
Size Tolerance

AbstractThe human visual system has a remarkable ability to reliably identify objects across variations in appearance, such as variations in viewpoint, lighting and size. Here we used fMRI in humans to test whether temporal contiguity training with natural and altered image dynamics can respectively build and break neural size tolerance for objects. Participants (N = 23) were presented with sequences of images of “growing” and “shrinking” objects. In half of the trials, the object also changed identity when the size change happened. According to the temporal contiguity hypothesis, and studies with a similar paradigm in monkeys, this training process should alter size tolerance. After the training phase, BOLD responses to each of the object images were measured in the scanner. Neural patterns in LOC and V1 contained information on size, similarity and identity. In LOC, the representation of object identity was partially invariant to changes in size. However, temporal contiguity training did not affect size tolerance in LOC. Size tolerance in human object-selective cortex is more robust to variations in input statistics than expected based on prior work in monkeys supporting the temporal contiguity hypothesis.

scholarly journals Automatic Detection of Transformer Components in Inspection Images Based on Improved Faster R-CNN

Energies ◽  
2018 ◽  
Vol 11 (12) ◽  
pp. 3496 ◽  
Author(s):  
Ziquan Liu ◽  
Huifang Wang
Keyword(s):  
Detection Accuracy ◽  
Training Process ◽  
Feature Maps ◽  
Size Change ◽  
Ordinary Objects ◽  
Detection Model ◽  
Significant Difference ◽  
High Detection ◽  
Practical Engineering ◽  
Improved Model

To detect the categories and positions of various transformer components in inspection images automatically, this paper proposes a transformer component detection model with high detection accuracy, based on the structure of Faster R-CNN. In consideration of the significant difference in component sizes, double feature maps are used to adapt to the size change, by adjusting two weights dynamically according to the object size. Moreover, different from the detection of ordinary objects, there is abundant useful information contained in the relative positions between components. Thus, the relative position features are defined and introduced to the refinement of the detection results. Then, the training process and detection process are proposed specifically for the improved model. Finally, an experiment is given to compare the accuracy and efficiency of the improved model and the original Faster R-CNN, along with other object detection models. Results show that the improved model has an obvious advantage in accuracy, and the efficiency is significantly higher than that of manual detection, which suggests that the model is suitable for practical engineering applications.

scholarly journals Unsupervised changes in core object recognition behavior are predicted by neural plasticity in inferior temporal cortex

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Xiaoxuan Jia ◽  
Ha Hong ◽  
Jim DiCarlo
Keyword(s):  
Object Recognition ◽  
Neural Plasticity ◽  
Time Course ◽  
Human Performance ◽  
Temporal Cortex ◽  
Neural Representation ◽  
Temporal Contiguity ◽  
Inferior Temporal Cortex ◽  
Object Identity ◽  
Visual Stream

Temporal continuity of object identity is a feature of natural visual input, and is potentially exploited -- in an unsupervised manner -- by the ventral visual stream to build the neural representation in inferior temporal (IT) cortex. Here we investigated whether plasticity of individual IT neurons underlies human core-object-recognition behavioral changes induced with unsupervised visual experience. We built a single-neuron plasticity model combined with a previously established IT population-to-recognition-behavior linking model to predict human learning effects. We found that our model, after constrained by neurophysiological data, largely predicted the mean direction, magnitude and time course of human performance changes. We also found a previously unreported dependency of the observed human performance change on the initial task difficulty. This result adds support to the hypothesis that tolerant core object recognition in human and non-human primates is instructed -- at least in part -- by naturally occurring unsupervised temporal contiguity experience.

scholarly journals Strategi Peningkatan Efektifitas Pelatihan Kepemimpinan: Telaah Teoretis dan Empiris

2018 ◽  
Vol 14 (1) ◽  
pp. 69-86
Author(s):  
Adi Suryanto
Keyword(s):  
Organizational Performance ◽  
System Design ◽  
Organizational Support ◽  
Leadership Training ◽  
Training System ◽  
Training Phase ◽  
Training Process ◽  
Effective Learning ◽  
Current Leadership

This article presents the idea of strategies for improving the effectiveness of leadership training that has so far not been clearly mapped. Although the current leadership training system design is perceived to be quite effective but in its perceived implementation it has not been optimal yet to boost organizational performance to the highest level. To focus the training into effective learning requires the organization to be able to pay attention to two important elements of training, participants characteristics and organizational support. Expectations of the two elements need to be met so that the training process runs perfectly. On this basis and with reference to empirical theories and experiences, this article successfully formulates three key strategies that need to be undertaken in the pre-leadership training phase, during leadership training, and post leadership training. Keywords : Effectiveness, Leadership Training Abstrak Artikel ini menyajikan pokok pikiran terkait strategi peningkatan efektivitas pelatihan kepemimpinan yang hingga saat ini masih belum terpetakan dengan jelas. Meskipun rancangan sistem pelatihan kepemimpinan yang ada saat ini dirasakan cukup efektif namun, dalam pelaksanannya dirasakan masih belum optimal mendongkrak kinerja organisasi ke level yang tertinggi. Untuk memfokuskan pelatihan menjadi pembelajaran yang efektif, mensyaratkan organisasi untuk mampu memperhatikan dua unsur penting yaitu karakteristik peserta pelatihan dan dukungan lingkungan organisasi. Ekspektasi dan harapan dua unsur tersebut perlu dipertemukan agar proses pelatihan berjalan sempurna. Atas dasar hal tersebut dan dengan berpedoman pada teori-teori dan pengalaman empiris, artikel ini berhasil memformulasikan tiga strategi utama yang perlu dijalankan mulai di fase pra-pelatihan kepemimpinan, pada saat pelatihan kepemimpinan, dan pasca pelatihan kepemimpinan. Kata Kunci : Efektivitas, Pelatihan Kepemimpinan

scholarly journals Why Do Line Drawings Work? A Realism Hypothesis

Perception ◽  
2020 ◽  
Vol 49 (4) ◽  
pp. 439-451 ◽  
Author(s):  
Aaron Hertzmann
Keyword(s):  
Visual System ◽  
Human Visual System ◽  
Line Drawing ◽  
Natural World ◽  
Human Observer ◽  
Object Identity ◽  
Line Drawings ◽  
3D Shape ◽  
Realistic Images ◽  
As If

Why is it that we can recognize object identity and 3D shape from line drawings, even though they do not exist in the natural world? This article hypothesizes that the human visual system perceives line drawings as if they were approximately realistic images. Moreover, the techniques of line drawing are chosen to accurately convey shape to a human observer. Several implications and variants of this hypothesis are explored.

Graded Size Sensitivity of Object-Exemplar–Evoked Activity Patterns Within Human LOC Subregions

2008 ◽  
Vol 100 (4) ◽  
pp. 2038-2047 ◽  
Author(s):  
Evelyn Eger ◽  
Christian A. Kell ◽  
Andreas Kleinschmidt
Keyword(s):  
Sensory Information ◽  
Size Difference ◽  
Support Vector ◽  
Visual Object ◽  
Visual Object Recognition ◽  
Object Identity ◽  
Invariant Representation ◽  
Size Change ◽  
Population Activity ◽  
Lateral Occipital Complex

A central issue for understanding visual object recognition is how the cortical hierarchy represents incoming sensory information and transforms it across successive processing stages. The format of object representation in the human brain has thus far mostly been studied using adaptation paradigms because the neuronal layout of object selectivities was thought to be beyond the resolution of conventional functional MRI (fMRI). Recently, however, multivariate pattern recognition succeeded in discriminating fMRI responses of object-selective cortex to different object exemplars within a given category. Here, we use increased spatial fMRI resolution to explore size sensitivity and tolerance to size change of response patterns evoked by object exemplars across a range of three sizes. Results from Support Vector Classification on responses of the human lateral occipital complex (LOC) show that discrimination of size (for a given object) and discrimination of objects across changes in size depended on the amount of size difference. Even across the largest amount of size change, accuracy for generalization was still significant in LOC, whereas the same comparison was at chance performance in early visual (calcarine) cortex. Analyzing subregions, we further found an anterior-posterior gradient in the degree of size sensitivity and size generalization within the posterior-dorsal and anterior-ventral parts of LOC. These results speak against fully size-invariant representation of object information in human LOC and are hence congruent with findings in monkeys showing object identity and size information in population activity of inferotemporal cortex. Moreover, these results provide evidence for a fine-grained functional heterogeneity within human LOC beyond the commonly used LO/fusiform subdivision.

scholarly journals Perceiving Illumination Inconsistencies in Scenes

Perception ◽  
10.1068/p5418 ◽  
2005 ◽  
Vol 34 (11) ◽  
pp. 1301-1314 ◽  
Author(s):  
Yuri Ostrovsky ◽  
Patrick Cavanagh ◽  
Pawan Sinha
Keyword(s):  
Visual System ◽  
Human Visual System ◽  
Rapid Detection ◽  
Prior Work ◽  
Illumination Direction ◽  
Global Consistency ◽  
Statistical Regularities

The human visual system is adept at detecting and encoding statistical regularities in its spatiotemporal environment. Here, we report an unexpected failure of this ability in the context of perceiving inconsistencies in illumination distributions across a scene. Prior work with arrays of objects all having uniform reflectance has shown that one inconsistently illuminated target can ‘pop out’ among a field of consistently illuminated objects (eg Enns and Rensink, 1990 Science247 721–723; Sun and Perona, 1997 Perception26 519–529). In these studies, the luminance pattern of the odd target could be interpreted as arising from either an inconsistent illumination or inconsistent pigmentation of the target. Either cue might explain the rapid detection. In contrast, we find that once the geometrical regularity of the previous displays is removed, the visual system is remarkably insensitive to illumination inconsistencies, both in experimental stimuli and in altered images of real scenes. Whether the target is interpreted as oddly illuminated or oddly pigmented, it is very difficult to find if the only cue is deviation from the regularity of illumination or reflectance. Our results allow us to draw inferences about how the visual system encodes illumination distributions across scenes. Specifically, they suggest that the visual system does not verify the global consistency of locally derived estimates of illumination direction.

scholarly journals Prefrontal Engagement during Source Memory Retrieval Depends on the Prior Encoding Task

2006 ◽  
Vol 18 (7) ◽  
pp. 1133-1146 ◽  
Author(s):  
Trudy Y. Kuo ◽  
Cyma Van Petten
Keyword(s):  
Prefrontal Cortex ◽  
Episodic Memory ◽  
Electrical Activity ◽  
Source Memory ◽  
Memory Retrieval ◽  
Healthy Subjects ◽  
Brain Electrical Activity ◽  
Object Identity ◽  
Prior Work ◽  
Memory Tests

The prefrontal cortex is strongly engaged by some, but not all, episodic memory tests. Prior work has shown that source recognition tests—those that require memory for conjunctions of studied attributes—yield deficient performance in patients with prefrontal damage and greater prefrontal activity in healthy subjects, as compared to simple recognition tests. Here, we tested the hypothesis that there is no intrinsic relationship between the prefrontal cortex and source memory, but that the prefrontal cortex is engaged by the demand to retrieve weakly encoded relationships. Subjects attempted to remember object/color conjunctions after an encoding task that focused on object identity alone, and an integrative encoding task that encouraged attention to object/color relationships. After the integrative encoding task, the late prefrontal brain electrical activity that typically occurs in source memory tests was eliminated. Earlier brain electrical activity related to successful recognition of the objects was unaffected by the nature of prior encoding.

scholarly journals Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization

2021 ◽  
Author(s):  
Nanda Kishore Sreenivas ◽  
Shrisha Rao
Keyword(s):  
Reinforcement Learning ◽  
Finite Number ◽  
Autonomous Vehicles ◽  
Safe Space ◽  
Training Phase ◽  
Prior Work ◽  
Industrial Systems ◽  
Learning Agent ◽  
Improved Performance ◽  
Action Spaces

In toy environments like video games, a reinforcement learning agent is deployed and operates within the same state space in which it was trained. However, in robotics applications such as industrial systems or autonomous vehicles, this cannot be guaranteed. A robot can be pushed out of its training space by some unforeseen perturbation, which may cause it to go into an unknown state from which it has not been trained to move towards its goal. While most prior work in the area of RL safety focuses on ensuring safety in the training phase, this paper focuses on ensuring the safe deployment of a robot that has already been trained to operate within a safe space. This work defines a condition on the state and action spaces, that if satisfied, guarantees the robot's recovery to safety independently. We also propose a strategy and design that facilitate this recovery within a finite number of steps after perturbation. This is implemented and tested against a standard RL model, and the results indicate a much-improved performance.

scholarly journals Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization

2021 ◽  
Author(s):  
Nanda Kishore Sreenivas ◽  
Shrisha Rao
Keyword(s):  
Reinforcement Learning ◽  
Finite Number ◽  
Autonomous Vehicles ◽  
Safe Space ◽  
Training Phase ◽  
Prior Work ◽  
Industrial Systems ◽  
Learning Agent ◽  
Improved Performance ◽  
Action Spaces

In toy environments like video games, a reinforcement learning agent is deployed and operates within the same state space in which it was trained. However, in robotics applications such as industrial systems or autonomous vehicles, this cannot be guaranteed. A robot can be pushed out of its training space by some unforeseen perturbation, which may cause it to go into an unknown state from which it has not been trained to move towards its goal. While most prior work in the area of RL safety focuses on ensuring safety in the training phase, this paper focuses on ensuring the safe deployment of a robot that has already been trained to operate within a safe space. This work defines a condition on the state and action spaces, that if satisfied, guarantees the robot's recovery to safety independently. We also propose a strategy and design that facilitate this recovery within a finite number of steps after perturbation. This is implemented and tested against a standard RL model, and the results indicate a much-improved performance.

scholarly journals Unsupervised changes in core object recognition behavior are predicted by neural plasticity in inferior temporal cortex

2020 ◽  
Author(s):  
Xiaoxuan Jia ◽  
Ha Hong ◽  
James J. DiCarlo
Keyword(s):  
Object Recognition ◽  
Neural Plasticity ◽  
Time Course ◽  
Human Performance ◽  
Temporal Cortex ◽  
Neural Representation ◽  
Temporal Contiguity ◽  
Inferior Temporal Cortex ◽  
Object Identity ◽  
Visual Stream

AbstractTemporal continuity of object identity is a feature of natural visual input, and is potentially exploited -- in an unsupervised manner -- by the ventral visual stream to build the neural representation in inferior temporal (IT) cortex and IT-dependent core object recognition behavior. Here we investigated whether plasticity of individual IT neurons underlies human behavioral changes induced with unsupervised visual experience by building a single-neuron plasticity model combined with a previously established IT population-to-recognition-behavior linking model to predict human learning effects. We found that our model quite accurately predicted the mean direction, magnitude and time course of human performance changes. We also found a previously unreported dependency of the observed human performance change on the initial task difficulty. This result adds support to the hypothesis that tolerant core object recognition in human and non-human primates is instructed -- at least in part -- by naturally occurring unsupervised temporal contiguity experience.

Sign in / Sign up

Export Citation Format

Share Document