Learning In Human Brain Research Articles

Novel Deep Learning Approach for Predicting Stock Market Trends

Stock Market Prediction a Major Achievement in financial markets is precisely forecasting stock market trends, which remains a considerable hurdle. Deep learning, a subset of machine learning, has grown to be a potent tool for untangling complex relationships within data. What distinguishes deep learning is its capacity to handle large amounts of data, unwrinkle difficult characteristics, and adapt to dynamic structures, all while unearthing concealed truths. Deep learning, at its core, is predicated on artificial neural networks that simulate human brain learning and pattern recognition capabilities, making it ideal for analyzing financial data. Through novel profound neural systems, the strategy applies a varied collection of the distributed showcase information, including, but not limited to, authentic stock costs, trading volumes, and calculations extracted from news sources. Keywords— stock advertise patterns, back, profound learning, designs, authentic information, design acknowledgment, sentiments.

Development of AI Models from Mammography Images with CNN for Early Detection of Breast Cancer

Early detection of breast cancer with computer assistance has developed since two decades ago. Artificial intelligence using the convolutional neural network (CNN) method has successfully predicted mammography images with a high level of accuracy similar to human brain learning. The potential of AI models provides opportunities to spot breast cancer cases better. This research aims to develop AI models with CNN using the public DDSM dataset with a sample size of 1871, consisting of 1546 images for training and 325 images for testing. These AI models provided prediction results with different accuracy rate. Increasing the accuracy of the AI model can be done by improving the image quality before the modeling process, increasing the number of datasets, or carrying out a more profound iteration process so that the AI model with CNN can have a better level of accuracy.

Bayesian Semiparametric Longitudinal Inverse-Probit Mixed Models for Category Learning.

Understanding how the adult human brain learns novel categories is an important problem in neuroscience. Drift-diffusion models are popular in such contexts for their ability to mimic the underlying neural mechanisms. One such model for gradual longitudinal learning was recently developed in Paulon et al. (J Am Stat Assoc 116:1114-1127, 2021). In practice, category response accuracies are often the only reliable measure recorded by behavioral scientists to describe human learning. Category response accuracies are, however, often the only reliable measure recorded by behavioral scientists to describe human learning. To our knowledge, however, drift-diffusion models for such scenarios have never been considered in the literature before. To address this gap, in this article, we build carefully on Paulon et al. (J Am Stat Assoc 116:1114-1127, 2021), but now with latent response times integrated out, to derive a novel biologically interpretable class of 'inverse-probit' categorical probability models for observed categories alone. However, this new marginal model presents significant identifiability and inferential challenges not encountered originally for the joint model in Paulon et al. (J Am Stat Assoc 116:1114-1127, 2021). We address these new challenges using a novel projection-based approach with a symmetry-preserving identifiability constraint that allows us to work with conjugate priors in an unconstrained space. We adapt the model for group and individual-level inference in longitudinal settings. Building again on the model's latent variable representation, we design an efficient Markov chain Monte Carlo algorithm for posterior computation. We evaluate the empirical performance of the method through simulation experiments. The practical efficacy of the method is illustrated in applications to longitudinal tone learning studies.

The role of lifelong machine learning in bridging the gap between human and machine learning: A scientometric analysis

AbstractDue to advancements in data collection, storage, and processing techniques, machine learning has become a thriving and dominant paradigm. However, one of its main shortcomings is that the classical machine learning paradigm acts in isolation without utilizing the knowledge gained through learning from related tasks in the past. To circumvent this, the concept of Lifelong Machine Learning (LML) has been proposed, with the goal of mimicking how humans learn and acquire cognition. Human learning research has revealed that the brain connects previously learned information while learning new information from a single or small number of examples. Similarly, an LML system continually learns by storing and applying acquired information. Starting with an analysis of how the human brain learns, this paper shows that the LML framework shares a functional structure with the brain when it comes to solving new problems using previously learned information. It also provides a description of the LML framework, emphasizing its similarities to human brain learning. It also provides citation graph generation and scientometric analysis algorithms for the LML literatures, including information about the datasets and evaluation metrics that have been used in the empirical evaluation of LML systems. Finally, it presents outstanding issues and possible future research directions in the field of LML.This article is categorized under: Technologies > Machine Learning

Changes in Cortical Microstructure of the Human Brain Resulting from Long-Term Motor Learning.

The mechanisms subserving motor skill acquisition and learning in the intact human brain are not fully understood. Previous studies in animals have demonstrated a causal relationship between motor learning and structural rearrangements of synaptic connections, raising the question of whether neurite-specific changes are also observable in humans. Here, we use advanced diffusion magnetic resonance imaging (MRI), sensitive to dendritic and axonal processes, to investigate neuroplasticity in response to long-term motor learning. We recruited healthy male and female human participants (age range 19-29) who learned a challenging dynamic balancing task (DBT) over four consecutive weeks. Diffusion MRI signals were fitted using Neurite Orientation Dispersion and Density Imaging (NODDI), a theory-driven biophysical model of diffusion, yielding measures of tissue volume, neurite density and the organizational complexity of neurites. While NODDI indices were unchanged and reliable during the control period, neurite orientation dispersion increased significantly during the learning period mainly in primary sensorimotor, prefrontal, premotor, supplementary, and cingulate motor areas. Importantly, reorganization of cortical microstructure during the learning phase predicted concurrent behavioral changes, whereas there was no relationship between microstructural changes during the control phase and learning. Changes in neurite complexity were independent of alterations in tissue density, cortical thickness, and intracortical myelin. Our results are in line with the notion that structural modulation of neurites is a key mechanism supporting complex motor learning in humans.SIGNIFICANCE STATEMENT The structural correlates of motor learning in the human brain are not fully understood. Results from animal studies suggest that synaptic remodeling (e.g., reorganization of dendritic spines) in sensorimotor-related brain areas is a crucial mechanism for the formation of motor memory. Using state-of-the-art diffusion magnetic resonance imaging (MRI), we found a behaviorally relevant increase in the organizational complexity of neocortical microstructure, mainly in primary sensorimotor, prefrontal, premotor, supplementary, and cingulate motor regions, following training of a challenging dynamic balancing task (DBT). Follow-up analyses suggested structural modulation of synapses as a plausible mechanism driving this increase, while colocalized changes in cortical thickness, tissue density, and intracortical myelin could not be detected. These results advance our knowledge about the neurobiological basis of motor learning in humans.

Project Prakash: Merging Basic Science and Societal Service in Vision Research

For nearly 20 years, Prakash has created a humanitarian-scientific synergy by treating congenitally blind children in rural India, then following their visual development to understand how the human brain learns to see. From solving a 300-year-old conundrum to deconstructing the “critical window” of neuroplasticity, Prakash has led to new ways of thinking about development. Unfortunately, many children suffering from treatable congenital blindness around the world remain untreated due to a persistent belief that improvements are not possible past a “critical age” of 5–7 years old. Here, a review of the data identifies an urgent need to engage with stakeholders across the global medical community to disseminate Prakash's findings and overturn these entrenched dogmas. Toward that end, recent partnerships with eye-health organizations expand the reach of this approach and cultivate a cohesive global network. Prakash exemplifies both evidence-based intervention and intervention-based scientific discovery.

Millimeter-wave radar object classification using knowledge-assisted neural network.

To improve the cognition and understanding capabilities of artificial intelligence (AI) technology, it is a tendency to explore the human brain learning processing and integrate brain mechanisms or knowledge into neural networks for inspiration and assistance. This paper concentrates on the application of AI technology in advanced driving assistance system. In this field, millimeter-wave radar is essential for elaborate environment perception due to its robustness to adverse conditions. However, it is still challenging for radar object classification in the complex traffic environment. In this paper, a knowledge-assisted neural network (KANN) is proposed for radar object classification. Inspired by the human brain cognition mechanism and algorithms based on human expertise, two kinds of prior knowledge are injected into the neural network to guide its training and improve its classification accuracy. Specifically, image knowledge provides spatial information about samples. It is integrated into an attention mechanism in the early stage of the network to help reassign attention precisely. In the late stage, object knowledge is combined with the deep features extracted from the network. It contains discriminant semantic information about samples. An attention-based injection method is proposed to adaptively allocate weights to the knowledge and deep features, generating more comprehensive and discriminative features. Experimental results on measured data demonstrate that KANN is superior to current methods and the performance is improved with knowledge assistance.

Classification of tumor from computed tomography images: A brain-inspired multisource transfer learning under probability distribution adaptation.

Preoperative diagnosis of gastric cancer and primary gastric lymphoma is challenging and has important clinical significance. Inspired by the inductive reasoning learning of the human brain, transfer learning can improve diagnosis performance of target task by utilizing the knowledge learned from the other domains (source domain). However, most studies focus on single-source transfer learning and may lead to model performance degradation when a large domain shift exists between the single-source domain and target domain. By simulating the multi-modal information learning and transfer mechanism of human brain, this study designed a multisource transfer learning feature extraction and classification framework, which can enhance the prediction performance of the target model by using multisource medical data (domain). First, this manuscript designs a feature extraction network that takes the maximum mean difference based on the Wasserstein distance as an adaptive measure of probability distribution and extracts the domain-specific invariant representations between source and target domain data. Then, aiming at the random generation of parameters bringing uncertainties to prediction accuracy and generalization ability of extreme learning machine network, the 1-norm regularization is used to implement sparse constraints of the output weight matrix and improve the robustness of the model. Finally, some experiments are carried out on the data of two medical centers. The experimental results show that the area under curves (AUCs) of the method are 0.958 and 0.929 in the two validation cohorts, respectively. The method in this manuscript can provide doctors with a better diagnostic reference, which has certain practical significance.

Multi-Task Learning Based on Stochastic Configuration Neural Networks.

When the human brain learns multiple related or continuous tasks, it will produce knowledge sharing and transfer. Thus, fast and effective task learning can be realized. This idea leads to multi-task learning. The key of multi-task learning is to find the correlation between tasks and establish a fast and effective model based on these relationship information. This paper proposes a multi-task learning framework based on stochastic configuration neural networks. It organically combines the idea of the classical parameter sharing multi-task learning with that of constraint sharing configuration in stochastic configuration neural networks. Moreover, it provides an efficient multi-kernel function selection mechanism. The convergence of the proposed algorithm is proved theoretically. The experiment results on one simulation data set and four real life data sets verify the effectiveness of the proposed algorithm.

Sentiment Analysis in British and American Literature Teaching under Formative Assessment and Machine Learning

In English education, British and American literature is a new type of course. The teaching of British and American literature has also undergone many reforms. In the practice of teaching reform, artificial intelligence- (AI-) assisted teaching such as machine learning (ML) has a long history. The performance is continuously improved by studying the mechanism of computer simulation of the human brain learning British and American literature. Then, computer intelligence can be realized. Based on this, this paper mainly discusses two aspects. One is the sentiment tendency analysis method based on the sentiment dictionary, and the other is the sentiment tendency analysis method based on ML. It mainly introduces the judgment of different emotional tendencies by the sentiment analysis model, which is an automatic review analysis and ensemble classification approach. The improvement of sentiment analysis improves the recognition range of text sentiment words in British and American literature teaching to optimize the process of text analysis. Its main feature is that the sentiment analysis of text directly acts on the tendency of words, with fine granularity and accurate analysis. Finally, it is concluded that the maximum value of the algorithm proposed here is 0.9, which has higher accuracy than the maximum value of 0.81 of other analysis models. The results indicate that the integrated classification model combining British and American literature teaching with the dimensions hidden Markov model has relatively reasonable text analysis and high sentiment classification accuracy. In terms of British and American literature teaching, using ML algorithms can effectively help teachers teach British and American literature through sentiment analysis.

Effect of an online module designed to promote first-year dental students' evidence-based study strategies.

The aim of this study was to investigate the effect of an online module in promoting study strategies based on neuroscience applied to education for first-year dental students at the University of the Andes in Santiago, Chile. Four weeks after the start of the 2018 first academic semester, all 82 first-year dental students (72% females, 28% males, average 19.0 years old) were invited to voluntarily and anonymously complete the self-reported Study Strategies Questionnaire (SSQ) in a session of an Introduction to Dentistry course, which served as a baseline. Subsequently, the session included an interactive workshop on learning how to learn so that students could analyse how the human brain learns and relate this information to mental tools to foster learning. Furthermore, during the semester, students were sent information via email to reinforce the content they were exposed to during the learning how to learn activity so that they could use the toolbox of study techniques to improve their learning in all subjects. At the end of the semester, students were invited to voluntarily and anonymously complete a second SSQ to assess the effects of the study intervention. Exam marks from the previous (2017) and studied year (2018), as well as both SSQ results, were compared and analysed using IBM Statistical Package for the Social Sciences (SPSS). A total of 75 and 71 students answered the SSQ before and after the intervention, respectively. The mean exam mark from 2017 was 63.7% (SD=8.8), whilst in 2018, it was 69.6% (SD=5.0) (p< .044); the effect size of the intervention was 0.75. The most significant changes observed after the intervention were reductions in the number of students who studied whilst checking messages on their smartphones (p= .001), studied by highlighting and/or underlining in their notes or textbooks (p ≤.0001) and studied the day before an examination (p≥ .0001). On the contrary, there were significant increases in the number of students who studied without access to social networks (p= .046), wrote notes or words in the margins of texts (p= .001), practised self-testing (p =.001) and studied the day before an examination (p≤ .0001). An online module to promote evidence-based study strategies in first-year dental students can have an impact on increasing students' marks as well as on some practices that can improve their academic achievements and learning.

Cognitive processes and neuroscientific epistemology

Developmental psychology analyzes the fundamental lines of study useful to explore the ways in which children represent reality. Specifically, considerable importance has been given to Piaget's model and the teory of Vygotskij. Today, neuroscience makes it possible to understand how the human brain learns such complex elements so quickly and from an early age. A long list of other data on behavioral and structural-physiological experiments highlights the fundamental role of activity in the formation of neuronal circuits and their adaptation to their function during the early postnatal stages. New experiences and new learning, and thus educational factors, can adjust the effectiveness of connections between nerve cells, intervening in the process of structural and functional modification of the brain. Much research indicates that there is a significant relationship between early experience and brain function.

The Impact of Math Manipulatives as a Multi-Sensory Teaching Technique in Statistics

Many students in social sciences have negative attitudes towards statistics courses, which are often excessively rigid, abstract, and employing teaching approaches that take much of the fun out of learning. A great deal of research has shown that the human brain learns and performs better in situations where information is integrated across several sensory modalities. Research also shows how multisensory teaching approaches are valuable in the learning of language and literacy, as well as for children with learning disabilities like dyslexia. Furthermore, many research studies have pointed out how math manipulatives contribute to students’ experiences by providing them with hands-on and concrete learning experiences. Currently, there seems to be a lack of research that incorporates math manipulatives as a multisensory teaching technique in introductory statistics courses. The purpose of this research is to investigate whether the use of math manipulatives as a multisensory teaching technique has an impact on students' academic performance in Statistics II at a South African university. A non-equivalent pretest posttest design was employed to see if the posttest performance of students exposed to the multisensory teaching strategy (in Statistics II) differed from that of students who received traditional instruction (in Business Statistics). The results of the study showed that students who were exposed to the multisensory teaching technique using math manipulatives achieved higher scores in Statistics II (µ = 70.18) than the students who were taught through traditional instruction (µ = 56.56). The study has significant implications on education, specifically for introductory statistics and probability.

Artificial synaptic behavior of the SBT-memristor* *Project supported by the National Natural Science Foundation of China (Grant Nos. 61703246 and 61703247), the Qingdao Science and Technology Plan Project (Grant No. 19-6-2-2-cg), and the Elite Project of Shandong University of Science and Technology.

The synapse of human brain neurons is not only the transmission channel of information, but also the basic unit of human brain learning and information storing. The artificial synapse is constructed based on the Sr0.97Ba0.03TiO3 – x (SBT) memristor, which realizes the short-term and long-term plasticity of the synapse. The experiential learning and non-associative learning behavior in accordance with human cognitive rules are realized by using the SBT-memristor-based synapse. The process of synaptic habituation and sensitization is analyzed. This study provides insightful guidance for realization of artificial synapse and the development of artificial neural network.

Synaptic metaplasticity emulation in a freestanding oxide-based neuromorphic transistor with dual in-plane gates

Synaptic plasticity is a basic characteristic of synapses and plays an important role in the computation, learning and memory of human brain. Metaplasticity is a higher-order form of synaptic plasticity, which regulates the ability of synapses to generate synaptic plasticity and has a great regulating effect on later learning, memory and coping behaviors. At present, there are rarely reports on the emulation of synaptic metaplasticity in synaptic transistor. In this article, flexible dual-gate indium-zinc-oxide neuromorphic devices on freestanding solid-state proton conducting chitosan electrolyte membrane are designed for metaplasticity emulation. The key synaptic plasticity functions including excitatory postsynaptic current, synaptic paired-pulse response and synaptic pulse train response can be effectively regulated by the priming pulse stimuli. Besides, configurable synaptic depression and synaptic potentiation effect can be realized in such device. These results can expand the potential applications of the multi-terminal electrolyte-gated oxide transistors for flexible dynamic neuromorphic platforms.

Microenseñanza para el desarrollo de competencias en la educación superior

The physical, biological, mental, psychological and emotional aspect is inert to the human being, it always accompanies in his life, in this respect, the knowledge of how the human brain learns has a great impact on education. Comprehending the brain mechanisms related to learning, genetic effects, context, emotions and age are some factors that support transforming educational strategies in order to make them more effective and better targeted, therefore, this article encloses a proposal in the concept of micro teaching to make better the meaningful learning on higher education.

Synaptic Characteristics of an Ultrathin Hexagonal Boron Nitride (h‐BN) Diffusive Memristor

A nano‐sized two‐terminal memristor exhibiting volatile threshold switching (TS) is a promising candidate for the emulation of biological synaptic functions to realize efficient neuromorphic computing systems. The Ca2+ dynamics play a vital role in generating a temporal response for neural functions by changing the synaptic weight of biological synapses. Herein, a thinnest synaptic device is fabricated demonstrating drift dynamics of Ag+ migration through the exfoliated h‐BN sheets, which emulates neuromorphic computing operations. The TS characteristics with a large ION/OFF up to ≈105 lead to bio‐synaptic applications, including short‐term and long‐term memory. The experimental realization of the synaptic behavior is demonstrated with paired‐pulse facilitation (PPF), spike‐rate‐dependent plasticity (SRDP), and transition from short‐term plasticity (STP) to long‐term plasticity (LTP). The transition from STP to LTP in this synaptic device verifies the Atkinson and Shiffrin psychological model of human brain learning experimentally. The input pulses with different spike‐times are used to replicate the synaptic functionalities. The two‐terminal diffusive memristors constructed with thin sheets of 2D‐flexible h‐BN resistive materials may lead to flexible neuromorphic devices for biological applications.

A Novel Identification Method for Apple (Malus domestica Borkh.) Cultivars Based on a Deep Convolutional Neural Network with Leaf Image Input

The innovation of germplasm resources and the continuous breeding of new varieties of apples (Malus domestica Borkh.) have yielded more than 8000 apple cultivars. The ability to identify apple cultivars with ease and accuracy can solve problems in apple breeding related to property rights protection to promote the healthy development of the global apple industry. However, the existing methods are inconsistent and time-consuming. This paper proposes an efficient and convenient method for the classification of apple cultivars using a deep convolutional neural network with leaf image input, which is the delicate symmetry of a human brain learning. The model was constructed using the TensorFlow framework and trained on a dataset of 12,435 leaf images for the identification of 14 apple cultivars. The proposed method achieved an overall accuracy of 0.9711 and could successfully avoid the over-fitting problem. Tests on an unknown independent testing set resulted in a mean accuracy, mean error, and variance of μ a c c = 0.9685 , μ ε = 0.0315 , and σ 2 = 1.89025 E − 4 , respectively, indicating that the generalization accuracy and stability of the model were very good. Finally, the classification performance for each cultivar was tested. The results show that model had an accuracy of 1.0000 for Ace, Hongrouyouxi, Jazz, and Honey Crisp cultivars, and only one leaf was incorrectly identified for 2001, Ada Red, Jonagold, and Gold Spur cultivars, with accuracies of 0.9787, 0.9800, 0.9773, and 0.9737, respectively. Jingning1 and Pinova cultivars were classified with the lowest accuracies, with 0.8780 and 0.8864, respectively. The results also show that the genetic relationship between cultivars Shoufu 3 and Yanfu 3 is very high, which is mainly because they were both selected from a red mutation of Fuji and bred in Yantai City, Shandong Province, China. Generally, this study indicates that the proposed deep learning model is a novel and improved solution for apple cultivar identification, with high generalization accuracy, stable convergence, and high specificity.

Bilateral Home Bias: A New Measure of Proximity

This paper uses recent developments from the fields of cognitive neuroscience and psycho-linguistics to introduce a new measure of proximity to the set of typical gravity variables in a model for bilateral home bias. Given the `weightlessness' of financial assets, gravity variables (among which geographical distance is the most prominent) are meaningful only as proxies for information or familiarity. The new measure of country similarity aims to directly capture the conceptual closeness of countries by comparing their semantic fingerprints. An AI solution which emulates the way the human brain learns and establishes associations among concepts, called the Retina engine, makes it possible to analyse text with human-level accuracy and to extract its semantic fingerprint (a numerical representation of meanings associated with the given term or a text). Akin to an artificial `investor' who has read virtually the entire Wikipedia, the Retina engine is able to quantify and compare textual descriptions of any pair of countries. In a model for bilateral home bias, the resulting measures of country similarity appear informative above and beyond distance and other gravity variables (common language, border, colonial link etc.). At its best, country similarity outperforms distance both in terms of statistical significance and impact on the dependent variable.

Research on Spatial Conceptual Modeling of Natural Language Processing Based on Deep Learning Algorithms

From the point of view of computer science, especially artificial intelligence, the task of natural language understanding is to establish a computer model. This computer model can give the result of understanding natural language like human. An important aspect of natural language understanding lies in how to express knowledge to the computer, how to express knowledge, and how to establish the connection and reasoning between knowledge, that is, how to apply the brain’s association, reasoning and selection process to the model of language processing. The physical structure and logical structure of modern computers are very clear, but what we need is a set of feasible formal thinking mechanism to enable machines to process natural language information. Deep learning is one of the areas of machine learning that is close to AI. It is analyzed by simulating human brain learning nerves. Deep learning is derived from the study of artificial neural networks and is a structure for learning deep nonlinear networks. By presenting complex function approximations, the input data is distributed and represented, and the ability of the data samples to focus on the essential characteristics of the data set is revealed.