scholarly journals Adaptive Tuning Curve Widths Improve Sample Efficient Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Florian Meier ◽  
Raphaël Dang-Nhu ◽  
Angelika Steger
Keyword(s):  
Tuning Curve ◽  
Adaptive Tuning ◽  
Efficient Learning

scholarly journals Adaptive Tuning Curve Widths Improve Sample Efficient Learning

2019 ◽  
Author(s):  
Florian Meier ◽  
Raphaël Dang-Nhu ◽  
Angelika Steger
Keyword(s):  
Machine Learning ◽  
Neural Coding ◽  
Learning Algorithm ◽  
Tuning Curve ◽  
Tuning Curves ◽  
Adaptive Tuning ◽  
Tuning Width ◽  
Population Codes ◽  
Low Dimensional ◽  
Efficient Learning

AbstractNatural brains perform miraculously well in learning new tasks from a small number of samples, whereas sample efficient learning is still a major open problem in the field of machine learning. Here, we raise the question, how the neural coding scheme affects sample efficiency, and make first progress on this question by proposing and analyzing a learning algorithm that uses a simple reinforce-type plasticity mechanism and does not require any gradients to learn low dimensional mappings. It harnesses three bio-plausible mechanisms, namely, population codes with bell shaped tuning curves, continous attractor mechanisms and probabilistic synapses, to achieve sample efficient learning. We show both theoretically and by simulations that population codes with broadly tuned neurons lead to high sample efficiency, whereas codes with sharply tuned neurons account for high final precision. Moreover, a dynamic adaptation of the tuning width during learning gives rise to both, high sample efficiency and high final precision. We prove a sample efficiency guarantee for our algorithm that lies within a logarithmic factor from the information theoretical optimum. Our simulations show that for low dimensional mappings, our learning algorithm achieves comparable sample efficiency to multi-layer perceptrons trained by gradient descent, although it does not use any gradients. Furthermore, it achieves competitive sample efficiency in low dimensional reinforcement learning tasks. From a machine learning perspective, these findings may inspire novel approaches to improve sample efficiency. From a neuroscience perspective, these findings suggest sample efficiency as a yet unstudied functional role of adaptive tuning curve width.

scholarly journals Task space adaptation via the learning of gait controllers of magnetic soft millirobots

2021 ◽  
pp. 027836492110218
Author(s):  
Sinan O. Demir ◽  
Utku Culha ◽  
Alp C. Karacakol ◽  
Abdon Pena-Francesch ◽  
Sebastian Trimpe ◽  
...  
Keyword(s):  
Human Body ◽  
Degrees Of Freedom ◽  
Bayesian Optimization ◽  
Small Scale ◽  
Soft Robots ◽  
Modeling And Control ◽  
Walking Gait ◽  
Physical Experiments ◽  
Efficient Learning ◽  
Task Environments

Untethered small-scale soft robots have promising applications in minimally invasive surgery, targeted drug delivery, and bioengineering applications as they can directly and non-invasively access confined and hard-to-reach spaces in the human body. For such potential biomedical applications, the adaptivity of the robot control is essential to ensure the continuity of the operations, as task environment conditions show dynamic variations that can alter the robot’s motion and task performance. The applicability of the conventional modeling and control methods is further limited for soft robots at the small-scale owing to their kinematics with virtually infinite degrees of freedom, inherent stochastic variability during fabrication, and changing dynamics during real-world interactions. To address the controller adaptation challenge to dynamically changing task environments, we propose using a probabilistic learning approach for a millimeter-scale magnetic walking soft robot using Bayesian optimization (BO) and Gaussian processes (GPs). Our approach provides a data-efficient learning scheme by finding the gait controller parameters while optimizing the stride length of the walking soft millirobot using a small number of physical experiments. To demonstrate the controller adaptation, we test the walking gait of the robot in task environments with different surface adhesion and roughness, and medium viscosity, which aims to represent the possible conditions for future robotic tasks inside the human body. We further utilize the transfer of the learned GP parameters among different task spaces and robots and compare their efficacy on the improvement of data-efficient controller learning.

scholarly journals Technology-mediated teaching and learning process: A conceptual study of educators’ response amidst the Covid-19 pandemic

2021 ◽  
Author(s):  
Kingsley Okoye ◽  
Jorge Alfonso Rodriguez-Tort ◽  
Jose Escamilla ◽  
Samira Hosseini
Keyword(s):  
Teaching And Learning ◽  
Linear Trend ◽  
Univariate Analysis ◽  
Learning Experiences ◽  
Well Being ◽  
Learning Tools ◽  
Main Challenge ◽  
Teachers And Students ◽  
Efficient Learning ◽  
Teaching Learning

AbstractThe COVID-19 pandemic has disrupted many areas of the human and organizational ventures worldwide. This includes new innovative technologies and strategies being developed by educators to foster the rapid learning-recovery and reinstatement of the stakeholders (e.g., teachers and students). Indeed, the main challenge for educators has been on what appropriate steps should be taken to prevent learning loss for the students; ranging from how to provide efficient learning tools/curriculum that ensures continuity of learning, to provision of methods that incorporate coping mechanisms and acceleration of education in general. For several higher educational institutions (HEIs), technology-mediated education has become an integral part of the modern teaching/learning instruction amidst the Covid-19 pandemic, when digital technologies have consequently become an inevitable and indispensable part of learning. To this effect, this study defines a hybrid educational model (HyFlex + Tec) used to enable virtual and in-person education in the HEIs. Practically, the study utilized data usage report from Massive Open Online Courses (MOOCs) and Emotions and Experience Survey questionnaire in a higher education setting for its experiments. To this end, we applied an Exponential Linear trend model and Forecasting method to determine overall progress and statistics for the learners during the Covid-19 pandemic, and subsequently performed a Text Mining and Univariate Analysis of Variance (ANOVA) to determine effects and significant differences that the teaching–learning experiences for the teachers and students have on their energy (learning motivation) levels. From the results, we note that the hybrid learning model supports continuity of education/learning for teachers and students during the Covid-19 pandemic. The study also discusses its innovative importance for future monitoring (tracking) of learning experiences and emotional well-being for the stakeholders in leu (aftermath) of the Covid-19 pandemic.

Attribute-efficient learning of Boolean functions from Post closed classes

2020 ◽  
Vol 30 (5) ◽  
pp. 285-301
Author(s):  
Anastasiya V. Bistrigova
Keyword(s):  
Boolean Functions ◽  
Membership Queries ◽  
Efficient Learning

AbstractWe consider exact attribute-efficient learning of functions from Post closed classes using membership queries and obtain bounds on learning complexity.

scholarly journals Adaptive Tuning of PID Controller using Crow Search Algorithm for DC motor

2021 ◽  
Vol 1076 (1) ◽  
pp. 012001
Author(s):  
Amer Alkrwy ◽  
Arkan Ahmed Hussein ◽  
Thamir H. Atyia ◽  
Muntadher Khamees
Keyword(s):  
Pid Controller ◽  
Search Algorithm ◽  
Dc Motor ◽  
Adaptive Tuning

scholarly journals Improving 3-m Resolution Land Cover Mapping through Efficient Learning from an Imperfect 10-m Resolution Map

2020 ◽  
Vol 12 (9) ◽  
pp. 1418
Author(s):  
Runmin Dong ◽  
Cong Li ◽  
Haohuan Fu ◽  
Jie Wang ◽  
Weijia Li ◽  
...  
Keyword(s):  
Land Cover ◽  
Training Data ◽  
Training Dataset ◽  
Land Cover Mapping ◽  
Remotely Sensed Data ◽  
Large Area ◽  
National Scale ◽  
Substantial Progress ◽  
Efficient Learning ◽  
Land Cover Maps

Substantial progress has been made in the field of large-area land cover mapping as the spatial resolution of remotely sensed data increases. However, a significant amount of human power is still required to label images for training and testing purposes, especially in high-resolution (e.g., 3-m) land cover mapping. In this research, we propose a solution that can produce 3-m resolution land cover maps on a national scale without human efforts being involved. First, using the public 10-m resolution land cover maps as an imperfect training dataset, we propose a deep learning based approach that can effectively transfer the existing knowledge. Then, we improve the efficiency of our method through a network pruning process for national-scale land cover mapping. Our proposed method can take the state-of-the-art 10-m resolution land cover maps (with an accuracy of 81.24% for China) as the training data, enable a transferred learning process that can produce 3-m resolution land cover maps, and further improve the overall accuracy (OA) to 86.34% for China. We present detailed results obtained over three mega cities in China, to demonstrate the effectiveness of our proposed approach for 3-m resolution large-area land cover mapping.

scholarly journals Selection for Reinforcement-Free Learning Ability as an Organizing Factor in the Evolution of Cognition

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Solvi Arnold ◽  
Reiji Suzuki ◽  
Takaya Arita
Keyword(s):  
Selection Pressure ◽  
Learning Ability ◽  
Environmental Complexity ◽  
Baldwin Effect ◽  
Neural Structure ◽  
Neural Organization ◽  
Environmental Structure ◽  
Selection For ◽  
Efficient Learning ◽  
Complexity Thesis

This research explores the relation between environmental structure and neurocognitive structure. We hypothesize that selection pressure on abilities for efficient learning (especially in settings with limited or no reward information) translates into selection pressure on correspondence relations between neurocognitive and environmental structure, since such correspondence allows for simple changes in the environment to be handled with simple learning updates in neurocognitive structure. We present a model in which a simple form of reinforcement-free learning is evolved in neural networks using neuromodulation and analyze the effect this selection for learning ability has on the virtual species' neural organization. We find a higher degree of organization than in a control population evolved without learning ability and discuss the relation between the observed neural structure and the environmental structure. We discuss our findings in the context of the environmental complexity thesis, the Baldwin effect, and other interactions between adaptation processes.

Does tinnitus originate from hyperactive nerve fibers in the cochlea?

1984 ◽  
Vol 98 (S9) ◽  
pp. 38-44 ◽  
Author(s):  
Richard S. Tyler
Keyword(s):  
Basilar Membrane ◽  
Tuning Curve ◽  
Nerve Fibers ◽  
Frequency Resolution ◽  
Signal Frequency ◽  
Physiological Data ◽  
Pitch Matching ◽  
Category Scaling ◽  
Tinnitus Masking ◽  
Peripheral Origin

AbstractThis paper discusses the possibility of a localized peripheral origin of tinnitus. A working hypothesis is that tinnitus represents either aperiodic or periodic hyperactivity in the spontaneous activity of nerve fibers originating from a restricted place on the basilar membrane. The limited physiological data available support both hyperactive and hypoactive nerve fiber. Psychophysical data are not easy to interpret. Subjective descriptions and category scaling are too dependent on individual experience. Pitch matching can be reliable, but cannot distinguish between peripheral or central tinnitus. In one experiment we compared the masking of tinnitus to the masking of a pure tone, where the signal frequency and level were obtained from the tinnitus pitch and loudness matching. The results indicate that the broad tinnitus masking patterns are not typically due to the poor frequency resolution observed in sensorineural hearing loss. However, in a few subjects there was some correspondence between the shape of the tuning curve and the tinnitus masking pattern. In another study, we masked tinnitus with narrowband noises of different bandwidths. In some patients, there was a ‘critical bandwidth’ effect; wider masker bandwidths required greater overall sound pressures to mask the tinnitus. We conclude that the results from these studies taken together indicate that there are different types of tinnitus, some of which may have a localized peripheral origin.

Sign in / Sign up

Export Citation Format

Share Document