FKPIndexNet: An efficient learning framework for finger-knuckle-print database indexing to boost identification

This chapter presents a highly scalable and adaptable co-learning framework on multimodal data mining in a multimedia database. The co-learning framework is based on the multiple instance learning theory. The framework enjoys a strong scalability in the sense that the query time complexity is a constant, independent of the database scale, and the mining effectiveness is also independent of the database scale, allowing facilitating a multimodal querying to a very large scale multimedia database. At the same time, this framework also enjoys a strong adaptability in the sense that it allows incrementally updating the database indexing with a constant operation when the database is dynamically updated with new information. Hence, this framework excels many of the existing multimodal data mining methods in the literature that are neither scalable nor adaptable at all. Theoretic analysis and empirical evaluations are provided to demonstrate the advantage of the strong scalability and adaptability. While this framework is general for multimodal data mining in any specific domains, to evaluate this framework, the authors apply it to the Berkeley Drosophila ISH embryo image database for the evaluations of the mining performance. They have compared the framework with a state-of-the-art multimodal data mining method to demonstrate the effectiveness and the promise of the framework.

Download Full-text

A Highly Scalable and Adaptable Co-Learning Framework on Multimodal Data Mining in a Multimedia Database

Data Mining ◽

10.4018/978-1-4666-2455-9.ch028 ◽

2013 ◽

pp. 567-586

Author(s):

Zhongfei (Mark) Zhang ◽

Zhen Guo ◽

Christos Faloutsos ◽

Jia-Yu Pan

Keyword(s):

Data Mining ◽

Large Scale ◽

Multiple Instance Learning ◽

Multimedia Database ◽

Multimodal Data ◽

Learning Framework ◽

New Information ◽

Database Indexing ◽

Constant Operation ◽

Multimodal Data Mining

This chapter presents a highly scalable and adaptable co-learning framework on multimodal data mining in a multimedia database. The co-learning framework is based on the multiple instance learning theory. The framework enjoys a strong scalability in the sense that the query time complexity is a constant, independent of the database scale, and the mining effectiveness is also independent of the database scale, allowing facilitating a multimodal querying to a very large scale multimedia database. At the same time, this framework also enjoys a strong adaptability in the sense that it allows incrementally updating the database indexing with a constant operation when the database is dynamically updated with new information. Hence, this framework excels many of the existing multimodal data mining methods in the literature that are neither scalable nor adaptable at all. Theoretic analysis and empirical evaluations are provided to demonstrate the advantage of the strong scalability and adaptability. While this framework is general for multimodal data mining in any specific domains, to evaluate this framework, the authors apply it to the Berkeley Drosophila ISH embryo image database for the evaluations of the mining performance. They have compared the framework with a state-of-the-art multimodal data mining method to demonstrate the effectiveness and the promise of the framework.

Download Full-text

Rules and mechanisms for efficient two-stage learning in neural circuits

10.1101/071910 ◽

2016 ◽

Cited By ~ 1

Author(s):

Tiberiu Teşileanu ◽

Bence Ölveczky ◽

Vijay Balasubramanian

Keyword(s):

Gradient Descent ◽

Temporal Structure ◽

Stochastic Gradient Descent ◽

Trial And Error ◽

Two Stage ◽

Plasticity Mechanism ◽

Learning Framework ◽

Error Learning ◽

Efficient Learning ◽

Teaching Signal

AbstractTrial-and-error learning requires evaluating variable actions and reinforcing successful variants. In songbirds, vocal exploration is induced by LMAN, the output of a basal ganglia-circuit that also contributes a corrective bias to the vocal output. This bias is gradually consolidated in RA, a motor cortex analogue downstream of LMAN. We develop a new model of such two-stage learning. Using stochastic gradient descent, we derive how the activity in ‘tutor’ circuits (e.g., LMAN) should match plasticity mechanisms in ‘student’ circuits (e.g., RA) to achieve efficient learning. We further describe a reinforcement learning framework through which the tutor can build its teaching signal. We show that mismatches between the tutor signal and the plasticity mechanism can impair learning. Applied to birdsong, our results predict the temporal structure of the corrective bias from LMAN given a plasticity rule in RA. Our framework can be applied predictively to other paired brain areas showing two-stage learning.

Download Full-text

Rules and mechanisms for efficient two-stage learning in neural circuits

eLife ◽

10.7554/elife.20944 ◽

2017 ◽

Vol 6 ◽

Cited By ~ 10

Author(s):

Tiberiu Teşileanu ◽

Bence Ölveczky ◽

Vijay Balasubramanian

Keyword(s):

Gradient Descent ◽

Temporal Structure ◽

Stochastic Gradient Descent ◽

Trial And Error ◽

Two Stage ◽

Plasticity Mechanism ◽

Learning Framework ◽

Error Learning ◽

Efficient Learning ◽

Teaching Signal

Trial-and-error learning requires evaluating variable actions and reinforcing successful variants. In songbirds, vocal exploration is induced by LMAN, the output of a basal ganglia-related circuit that also contributes a corrective bias to the vocal output. This bias is gradually consolidated in RA, a motor cortex analogue downstream of LMAN. We develop a new model of such two-stage learning. Using stochastic gradient descent, we derive how the activity in ‘tutor’ circuits (e.g., LMAN) should match plasticity mechanisms in ‘student’ circuits (e.g., RA) to achieve efficient learning. We further describe a reinforcement learning framework through which the tutor can build its teaching signal. We show that mismatches between the tutor signal and the plasticity mechanism can impair learning. Applied to birdsong, our results predict the temporal structure of the corrective bias from LMAN given a plasticity rule in RA. Our framework can be applied predictively to other paired brain areas showing two-stage learning.

Download Full-text

Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation

Medical Image Analysis ◽

10.1016/j.media.2021.102263 ◽

2021 ◽

pp. 102263

Author(s):

Vien Ngoc Dang ◽

Francesco Galati ◽

Rosa Cortese ◽

Giuseppe Di Giacomo ◽

Viola Marconetto ◽

...

Keyword(s):

Learning Framework ◽

Efficient Learning

Download Full-text

A Sparsity-Driven Backpropagation-Less Learning Framework Using Populations of Spiking Growth Transform Neurons

Frontiers in Neuroscience ◽

10.3389/fnins.2021.715451 ◽

2021 ◽

Vol 15 ◽

Author(s):

Ahana Gangopadhyay ◽

Shantanu Chakrabartty

Keyword(s):

Dynamic Range ◽

Energy Functional ◽

Learning Approach ◽

Learning Framework ◽

Wide Range ◽

Sparsity Constraints ◽

Training Error ◽

Machine Olfaction ◽

Efficient Learning ◽

Spiking Activity

Growth-transform (GT) neurons and their population models allow for independent control over the spiking statistics and the transient population dynamics while optimizing a physically plausible distributed energy functional involving continuous-valued neural variables. In this paper we describe a backpropagation-less learning approach to train a network of spiking GT neurons by enforcing sparsity constraints on the overall network spiking activity. The key features of the model and the proposed learning framework are: (a) spike responses are generated as a result of constraint violation and hence can be viewed as Lagrangian parameters; (b) the optimal parameters for a given task can be learned using neurally relevant local learning rules and in an online manner; (c) the network optimizes itself to encode the solution with as few spikes as possible (sparsity); (d) the network optimizes itself to operate at a solution with the maximum dynamic range and away from saturation; and (e) the framework is flexible enough to incorporate additional structural and connectivity constraints on the network. As a result, the proposed formulation is attractive for designing neuromorphic tinyML systems that are constrained in energy, resources, and network structure. In this paper, we show how the approach could be used for unsupervised and supervised learning such that minimizing a training error is equivalent to minimizing the overall spiking activity across the network. We then build on this framework to implement three different multi-layer spiking network architectures with progressively increasing flexibility in training and consequently, sparsity. We demonstrate the applicability of the proposed algorithm for resource-efficient learning using a publicly available machine olfaction dataset with unique challenges like sensor drift and a wide range of stimulus concentrations. In all of these case studies we show that a GT network trained using the proposed learning approach is able to minimize the network-level spiking activity while producing classification accuracy that are comparable to standard approaches on the same dataset.

Download Full-text

A Preliminary Study on a Physical Model Oriented Learning Algorithm With Application to UAVs

Volume 3, Rapid Fire Interactive Presentations: Advances in Control Systems; Advances in Robotics and Mechatronics; Automotive and Transportation Systems; Motion Planning and Trajectory Tracking; Soft Mechatronic Actuators and Sensors; Unmanned Ground and Aerial Vehicles ◽

10.1115/dscc2019-9186 ◽

2019 ◽

Cited By ~ 4

Author(s):

Minghui Zheng ◽

Zhu Chen ◽

Xiao Liang

Keyword(s):

Physical Model ◽

Learning Algorithm ◽

Feedforward Control ◽

Utilization Efficiency ◽

Learning From Errors ◽

Learning Capability ◽

Learning Framework ◽

Model Mapping ◽

Preliminary Study ◽

Efficient Learning

Abstract This paper provides a preliminary study for an efficient learning algorithm by reasoning the error from first principle physics to generate learning signals in near real time. Motivated by iterative learning control (ILC), this learning algorithm is applied to the feedforward control loop of the unmanned aerial vehicles (UAVs), enabling the learning from errors made by other UAVs with different dynamics or flying in different scenarios. This learning framework improves the data utilization efficiency and learning reliability via analytically incorporating the physical model mapping, and enhances the flexibility of the model-based methodology with equipping it with the self-learning capability. Numerical studies are performed to validate the proposed learning algorithm.

Download Full-text

Relevant Influence of Semantic Web Framework on Smart E-Learning Environment

International Journal of Emerging Technologies in Learning (iJET) ◽

10.3991/ijet.v16i17.24105 ◽

2021 ◽

Vol 16 (17) ◽

pp. 177

Author(s):

Subhabrata Sengupta ◽

Anish Banerjee ◽

Satyajit Chakrabarti

Keyword(s):

Online Learning ◽

Semantic Web ◽

Learning Objects ◽

Learning System ◽

Semantic Web Technologies ◽

Educational Management ◽

Learning Framework ◽

Self Organized ◽

E Learning ◽

Efficient Learning

E-Learning systems have unbound prospects to deliver unmatched effective learning services and feedback assistance than what it is presently offering through mediums like online tutoring, or other electronic educational management services. Different stages and application potentials of Semantic Web technology and it’s architecture can be applied at different sectors and phases of the E-Learning framework to amplify the quality and versatility of services. Features of Semantic Web have been explored in the sectors with respect to instructors to plan, analyse and execute their tasks and also in making a sustainable system that interprets the structure of distributed, self organized, and self-instructed online learning to monitor it’s influence on performance. The main objective of this work is to study how electronic and online learning frameworks can be improved and enhanced by the influence of semantic web technologies in understanding and simplifying concept clarification and description, reusable learning objects (LOs), and benefits of the applying ontology in describing the learning materials for a better and more efficient learning system.

Download Full-text

Automated Spectral Kernel Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5892 ◽

2020 ◽

Vol 34 (04) ◽

pp. 4618-4625

Author(s):

Jian Li ◽

Yong Liu ◽

Weiping Wang

Keyword(s):

Error Bounds ◽

Kernel Methods ◽

Experimental Results ◽

Kernel Learning ◽

Generalization Error ◽

Learning Framework ◽

Model Training ◽

Efficient Learning ◽

Spectral Representations ◽

Spectral Kernel

The generalization performance of kernel methods is largely determined by the kernel, but spectral representations of stationary kernels are both input-independent and output-independent, which limits their applications on complicated tasks. In this paper, we propose an efficient learning framework that incorporates the process of finding suitable kernels and model training. Using non-stationary spectral kernels and backpropagation w.r.t. the objective, we obtain favorable spectral representations that depends on both inputs and outputs. Further, based on Rademacher complexity, we derive data-dependent generalization error bounds, where we investigate the effect of those factors and introduce regularization terms to improve the performance. Extensive experimental results validate the effectiveness of the proposed algorithm and coincide with our theoretical findings.

Download Full-text