Gradient Population Optimization: A Tensorflow-Based Heterogeneous Non-Von-Neumann Paradigm for Large-Scale Search

Persano, John; Mikki, Said; Antar, Yahia M. M.

doi:10.1109/access.2018.2868236

Cited by 6 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We embrace below the now well-established trend of treating AI systems as essentially dynamic agents [72]. This view is fundamental for future realizations of AGI using networks or assemblages of multiple interacting agents [45], [46], [87]- [89].…”

Section: B Dynamical Systems and Intelligencementioning

confidence: 99%

“…To simplify the presentation, we only state the rules for one agent. However, as in other population-based AI methods, assemblages of interacting agents can be set to evolve in time, with engineered or programmed interaction Hamiltonian such that their global behaviour may lead to a solution to a problem, hence exhibiting intelligent behaviour [45], [87]- [89], [91], [100]. Moreover, each subsystem described by a law like (2) can be non-Markovian due to the existence of nontrivial history operator L [118], [120].…”

Section: A the Single Agent System Level Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial General Intelligence, Noncomputability, and Dynamical Systems: A Critical Reexamination

Mikki¹

2022

Preprint

View full text Add to dashboard Cite

<p>Achieving genuine (human-level) artificial general intelligence (AGI) is one of the major goals of computer science, engineering, psychology, and mathematics. In this article, we critically reexamine the relation between natural intelligence and artificial intelligence at a fairly general theoretical level. After identifying four major structural themes in natural intelligence, we move to the issue of AGI implementation through physical computing machines. Motivated by Penrose’s G¨ddelian argument refuting the thesis of AGI realizability via Turing machines, we formulate several theses on the noncomputable essence of AGI systems and suggest that infinitary noncomputability might constitute a viable path toward future AGI implementations, especially if coupled with nonlocality and a non-classical probabilistic structure such as the quantum case. A theoretical mathematical framework for non-Markovian stochastic dynamic systems is then presented and illustrated by describing multiagent AGI assemblages comprised of interconnected dynamic agents. We envision that such networked dynamical assemblages might be powered by noncomputable physics or arranged in an infinitary structure.</p>

show abstract

Section: B Dynamical Systems and Intelligencementioning

confidence: 99%

Section: A the Single Agent System Level Descriptionmentioning

confidence: 99%

Artificial General Intelligence, Noncomputability, and Dynamical Systems: A Critical Reexamination

Mikki¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The first part is to find a lower bound for f ( ), which is similar to Corollary 1, and the second part is to analyze the optimal configuration. From (29), it is obvious that f ( ) is upper bounded by…”

Section: A Angle Changing Casementioning

confidence: 99%

“…After the data set and label set are constructed according to the input and output of the neural network for UAV heading decision-making, the off-line training and learning of the network is carried out by using Tensorflow platform [29]. Fig.…”

Section: Off-line Network Training Testmentioning

confidence: 99%

Optimal Configuration Analysis of AOA Localization and Optimal Heading Angles Generation Method for UAV Swarms

et al. 2019

View full text Add to dashboard Cite

In this paper, the angle-of-arrival (AOA) measurements are adapted to locate a target using the UAV swarms equipped with passive receivers. The measurement noise is considered to be target-to-receiver distance dependent. The Cramer-Rao low bound (CRLB) of the AOA localization is calculated, and the optimal deployments are explored through changing angular separations and distances. Then, a distributed collaborative autonomous generation (DCAG) method is proposed based on the deep neural network (NN). The off-line training and on-line application rules are applied to generate the optimal heading angles for the UAV swarms in the AOA localization. The simulation results show that through the DCAG method, the generated heading angles for UAV swarms enhance the localization accuracy and stability. INDEX TERMS AOA localization, distributed collaborative autonomous generation (DCAG), Cramer-Rao low bound (CRLB), deep neural network (NN).

show abstract

“…Recently, TensorFlow [18]- [20], open-source software that provides a stable platform for CNN deep learning, has been used in various research studies and applications that include identifying plants [6], [21], [22] and plant diseases [23], [24]. Automatic herb identification is a helpful support system for botanical education and surveying.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for Herb Identification: Plain Background and Natural Environment

Chaivivatrakul¹,

Moonrinta²,

Chaiwiwatrakul³

2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Convolutional neural networks have achieved success in resolving object identification problems. This study contributes a suitable new approach to herb identification for educational and research purposes based on a small dataset and small-sized images. Two self-collected Thai herb datasets with either plain or natural environment backgrounds were used for experimentation to realize this objective. The plain background dataset includes 4,400 images of 11 leaf types, and the natural dataset contains 1,620 images of nine leaf types. The images were divided into a training set containing 75% of the images and a separate test set with the remaining 25%. The experiments included five-fold cross-validation applied to the training set; the InceptionV3, MobileNetV2, ResNet50V2, VGG16, and Xception convolutional neural network models RMSprop and Adam optimizers. Further, dropout rates of 0.3, 0.5, and 0.7 were considered along with five and ten epochs. Transfer learning was applied using pre-trained weights. The model with the best outcome, based on the average accuracy of the cross-validation results on both datasets (the plain background dataset was 94.55%, and the natural dataset was 90.37%), was the VGG16 with the RMSprop optimizer, which exhibited a dropout rate of 0.5 over ten epochs. The model achieved 96.64% and 92.00% accuracy on the plain background training and test sets, and 99.59% and 91.36% on the natural environment training and test sets, respectively. The results show that the method has a high potential for objective tasks and application in identifying herbs based on visual leaf information.

show abstract

Gradient Population Optimization: A Tensorflow-Based Heterogeneous Non-Von-Neumann Paradigm for Large-Scale Search

Cited by 6 publications

References 39 publications

Artificial General Intelligence, Noncomputability, and Dynamical Systems: A Critical Reexamination

Artificial General Intelligence, Noncomputability, and Dynamical Systems: A Critical Reexamination

Optimal Configuration Analysis of AOA Localization and Optimal Heading Angles Generation Method for UAV Swarms

Convolutional Neural Networks for Herb Identification: Plain Background and Natural Environment

Contact Info

Product

Resources

About