Simple Learning Model Research Articles

The Age of the Meta-Doctor: Diagnosing Parkinson’s Disease with Artificial Intelligence and Speech

The basal ganglia consist of the striatum, substantia nigra, and other nuclei, forming various pathways of motor initiation. Parkinson’s disease (PD) is a neurodegenerative disorder characterized by dysfunction of the basal ganglia pathways. Consequently, PD affects the production of speech. An AI model can analyze audio samples from regular and PD patients. A simple deep learning model with various layers, ReLU activation, sigmoid activation, optimizer, loss function, and Early_Stopping can use extracted speech features to classify patients as regular or PD-afflicted with up to 97% accuracy. Overall, the advent of user-friendly artificial intelligence has led to exciting times, with new medical advancements emerging day after day; perhaps the ease of AI implementation will encourage others to solve everyday problems with just a computer and a dream.

Physiological characterization of instrumental learning in the spinal cord using the Paw Withdrawal Learning paradigm

Following spinal cord injury (SCI), sensory and motor functions are severely disrupted yet the spinal circuitry below the injury site continues to maintain active and functional neuronal properties (Edgerton, 2004). The spinal cord is endogenously capable of several forms of adaptive plasticity, including functional re-training with exercise, instrumental, and Pavlovian learning. The paw withdrawal learning (PaWL) paradigm represents a simple spinal instrumental learning model (Jindrich 2019). Briefly, in mice whose spinal cords are completely transected (ST) at mid-thoracic (T7-T9) level, the tibialis anterior (TA) muscle is given a sub maximal threshold shock to a hind leg when the leg is extended below a 1mm imposed threshold from a baseline starting position. The contingent group mice learn to maintain the shocked leg, in a flexed position while the experimentally coupled noncontingent group of mice do not acquire the flexed position. To demonstrate the acquisition of the flexed paw hold is mediated through muscle-specific proprioceptive inputs and a time dependent modification of the spinal interneuronal network associated with the TA motor pool, we measured the TA muscle activity using acute EMG during PaWL in both Contingent stim and non-contingent stim groups. To demonstrate that TA specific sensory afferents are critical in PaWL, we blocked the proprioceptive muscle and the cutaneous afferents using Lidocaine. During PaWL, the TA muscle showed significant EMG activity when compared to medial gastrocnemius and vastus lateralis muscles. We detected greater TA muscle activity in the Contingent stim compared to the non-contingent groups. The significant increase in the EMG amplitude in the TA muscle and time-frequency and power relationships in the contingent group, but not the non-contingent group, suggests that the successful learning requires a temporal engagement of the spinal sensorimotor network. CSULA Mini-Grant 2020 and Joseph/Gomez-Pinilla R01NS056413 (Diversity Supplement) This is the full abstract presented at the American Physiology Summit 2023 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

LSTM-GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios.

In the present work, the volatility of the leading cryptocurrencies is predicted through generalised autoregressive conditional heteroskedasticity (GARCH) models, multilayer perceptron(MLP), long short-term memory (LSTM), and hybrid models of the type LSTM and GARCH, where parameters of the GARCH family are included as features of LSTM models. The study period covered the scenario of the World Health Organization pandemic declaration around March 2020 at hourly frequency. We have found that the different variants of deep neural network models outperform those of the GARCH family in the sense of the hetorerocedastic error, and absolute and squared error(HSE). Under the sharpe ratio, the volatility forecasting of a uniform portfolio at long horizons systematically outperforms the stablecoin Tether, which is considered here as the risk-free asset. Also, including transaction volume helps reduce the value at risk or loss probability for the uniform portfolio. Moreover, in a minimum variance portfolio, it is observed that before the pandemic declaration, a large proportion of the capital was allocated to bitcoin(BTC). In contrast, after March 2020, the portfolio is more diversified with short positions for BTC. Moreover, the MLP models give the best predictive results, although not statistically different in accuracy compared to the LSTM and LSTM-GARCH versions under the Diebold-Mariano test. In sum, MLP models outperform most stylised financial models and are less computationally expensive than more complex neural networks. Therefore, simple learning models are suggested in highly non-linear time series volatility forecasts as it is the cryptocurrency market.

Discriminative Local Representation Learning for Cross-Modality Visible-Thermal Person Re-Identification

Visible-thermal person re-identification (VTReID) is a rising and challenging cross-modality retrieval task in intelligent video surveillance systems. Most attention architectures cannot explore the discriminative person representations for VTReID, especially in the thermal modality. In addition, the fine-grained middle-level semantic information has received much less attention in the part-based approaches for the cross-modality pedestrian retrieval task, resulting in limited generalization capability and poor representation robustness. This paper proposes a simple yet powerful discriminative local representation learning (DLRL) model to capture the robust local fine-grained feature representations and explore the rich semantic relationship between the learned part features. Specifically, an efficient contextual attention aggregation module (CAAM) is designed to strengthen the discriminative capability of the feature representations and explore the contextual cues for visible and thermal modalities. Then, an integrated middle-high feature learning (IMHF) method is introduced to capture the part-level salient representations, which handles the ambiguous modality discrepancy in both discriminative middle-level and robust high-level information. Moreover, a part-guided graph convolution module (PGCM) is constructed to mine the structural relationship among the part representations within each modality. The quantitative and qualitative experiments on the two benchmark datasets demonstrate that the proposed DLRL model significantly outperforms state-of-the-art methods and achieves rank-1/mAP accuracy of 92.77%/82.05% on the RegDB dataset and 63.04%/60.58% on the SYSU-MM01 dataset.

Cholinergic activity reflects reward expectations and predicts behavioral responses

Basal forebrain cholinergic neurons (BFCNs) play an important role in associative learning, suggesting that BFCNs may participate in processing stimuli that predict future outcomes. However, the impact of outcome probabilities on BFCN activity remained elusive. Therefore, we performed bulk calcium imaging and recorded spiking of identified cholinergic neurons from the basal forebrain of mice performing a probabilistic Pavlovian cued outcome task. BFCNs responded more to sensory cues that were often paired with reward. Reward delivery also activated BFCNs, with surprising rewards eliciting a stronger response, whereas punishments evoked uniform positive-going responses. We propose that BFCNs differentially weigh predictions of positive and negative reinforcement, reflecting divergent relative salience of forecasting appetitive and aversive outcomes, partially explained by a simple reinforcement learning model of a valence-weighed unsigned prediction error. Finally, the extent of cue-driven cholinergic activation predicted subsequent decision speed, suggesting that the expectation-gated cholinergic firing is instructive to reward-seeking behaviors.

Micro-network Based Convolutional Neural Network with Integration of Multilayer Feature Fusion Strategy for Human Activity Recognition

Convolutional neural networks (CNN) have shown remarkable performance in enormous computer vision applications over the years, and many works have been done for human activity recognition (HAR) using CNN. However, most of deep learning-based architectures require large training data and plenty of computational resources. Therefore, we proposed a simple and efficient deep learning model for human activity recognition, which works on complex visual data and require less computational resources. In the proposed work, we designed a novel CNN architecture by stacking the repeated components called micro-networks to incorporate multiscale processing in the network layers. We have used a feature fusion strategy to pass the previous layer’s abstract complementary information to the next adjacent layer, believing that each layer encapsulates specific feature maps. Therefore, the hidden complementary information can potentially enhance the feature discrimination capacity of the network and help in learning the network. The proposed architecture is fully trained from scratch with stochastic gradient descent (SGD) optimizer at 0.05 initial learning rate and a softmax classifier is used for activity recognition. The merit of the proposed method over standard deep learning models is its computational efficiency in terms of learnable parameters and computational resources. The proposed model gives good performance on small as well as large size datasets. For authentication of the proposed method several extensive experiments are conducted on publically available datasets, namely UCF-101, HMDB-51, YouTube, and IXMAS datasets. The results have shown the outperformance of the proposed method over the existing state-of-the-art methods.

EchoWrite 2.0: A Lightweight Zero-Shot Text-Entry System Based on Acoustics

Limited by size, shape, and other factors, it is rather inconvenient to interact with new smart devices by traditional methods. Acoustic-based methods following a machine learning approach have been put forward to resolve this problem in previous works. But they possess limitations of heavy training overhead, low performance for unseen users, and intensive computation cost. Following our previous work in this area, we further overcome shortcomings of existing work and propose a lightweight and zero-shot text-entry system for unseen users based on acoustic sensing. The key novelty of this work is proposing a new model training strategy including dataset construction and augmentation methods to effectively enhance generalization ability of a simple learning model with as few training data as possible, based on our insight into the problem. We design and implement a real-time Android application system called <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EchoWrite 2.0</monospace> to validate our idea with extensive experiments. Results show that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EchoWrite 2.0</monospace> can recognize digits, English letters, and words with an accuracy of 85.3%, 73.2%, and 96.9%, respectively, for unseen users without providing any data to the learning model. The comparison with related work in different aspects shows overall superiority of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EchoWrite 2.0</monospace> .

A facial expression recognition method based on Convolutional Neural Network

This project is the implementation method of a simple static facial expression recognition (FER) project. Under the environment of Python3, the deep learning model is used to compare with the traditional model. Finally, CNN (Convolutional Neural Networks) is actually used to construct the entire system, and model evaluation is carried out on the three FER datasets FER2013, JAFFE and CK+. The project's main functions include "get a picture of a person's face" and "recognize expressions". The principles of the above functions include the following: the establishment of neural network structure, the acquisition of data sets, the model training based on data sets, the use of OpenCV to obtain the face, and the use of the model to recognize the expression. The experimental results reproduce the simple deep learning model to realize FER and verify the different effects of different data sets on the results. Face recognition has been widely used in all aspects of life, but different purposes need different models and data collection methods, and the laboratory collection cost is high, and the amount of data is limited, so this project also discusses the data set selection methods under different purposes.

Relative stability toward diffeomorphisms indicates performance in deep nets* *This article is an updated version of: Petrini L, Favero A, Geiger M and Wyart M 2021 Relative stability toward diffeomorphisms indicates performance in deep nets Advances in Neural Information Processing Systems vol 34 ed M Ranzato, A Beygelzimer, Y Dauphin, P S Liang and J Wortman Vaughan (New York: Curran

Understanding why deep nets can classify data in large dimensions remains a challenge. It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empirical measurements support that it is often not the case. We revisit this question by defining a maximum-entropy distribution on diffeomorphisms, that allows to study typical diffeomorphisms of a given norm. We confirm that stability toward diffeomorphisms does not strongly correlate to performance on benchmark data sets of images. By contrast, we find that the stability toward diffeomorphisms relative to that of generic transformations R f correlates remarkably with the test error ϵ t. It is of order unity at initialization but decreases by several decades during training for state-of-the-art architectures. For CIFAR10 and 15 known architectures we find , suggesting that obtaining a small R f is important to achieve good performance. We study how R f depends on the size of the training set and compare it to a simple model of invariant learning.

Penerapan Model Pembelajaran Index Card Match Untuk Meningkatkan Motivasi Belajar Siswa Pada Pembelajaran Sosiologi

This study aims to apply the index card match learning model to increase students' motivation to learn sociology in class XI IPS 2 SMAN 1 Rao Utara. The results of this study will be helpful for teachers as a guide in implementing a simple and fun learning model for students. By looking at the purpose of this research, it can be seen that this type of research is classroom action research (CAR), where the data collection technique that the author does is through the observation sheet. The subjects of this study consisted of 22 students in class XI IPS 2. Then the resulting data will be analyzed with quantitative descriptive techniques so that the resulting data can be tested for validity. The indicator of the success of this research leads to the average percentage of students' motivation in classical sociology learning, which is at least 70%. The results showed an increase in students' motivation to learn sociology. The pre-cycle found students' learning motivation with an average score of 15.58%, then in the first cycle of 42.85%, and the second cycle of 72.72%. Thus, this learning model has succeeded in increasing students' motivation to learn sociology in class XI IPS 2 SMAN 1 Rao Utara.

Hybrid Learning Model in the Teaching and Learning Process Basic Accounting Practice

This research is aimed at designing an efficient hybrid learning model in learning Basic Accounting Practices. This learning model is expected to be used as a guide by lecturers who support courses in planning, implementing and evaluating their learning activities. The hardware used is a Laptop, Web Camera, Bluetooth Headset, LCD Projector, while the software is Google Meet. Research activities are carried out through 3 stages, namely: program planning, development and implementation, evaluation. The target subjects are students of the Bali State Polytechnic Accounting Department in semester 2, the target object is a learning device for the Basic Accounting Practice course. The results show that this simple hybrid learning model can be applied effectively in learning Basic Accounting Practices. This is indicated by the level of student satisfaction with the reliability of the learning model (material, design, media) using the 5 scale is an average of 4.0 (Satisfied) with an average learning outcome value of 81.01 (A). Suggestions from students are the need for reliable Wi-Fi and LCD projector facilities in every classroom.

Learned lensless 3D camera.

Single-shot three-dimensional (3D) imaging with compact device footprint, high imaging quality, and fast processing speed is challenging in computational imaging. Mask-based lensless imagers, which replace the bulky optics with customized thin optical masks, are portable and lightweight, and can recover 3D object from a snap-shot image. Existing lensless imaging typically requires extensive calibration of its point spread function and heavy computational resources to reconstruct the object. Here we overcome these challenges and demonstrate a compact and learnable lensless 3D camera for real-time photorealistic imaging. We custom designed and fabricated the optical phase mask with an optimized spatial frequency support and axial resolving ability. We developed a simple and robust physics-aware deep learning model with adversarial learning module for real-time depth-resolved photorealistic reconstructions. Our lensless imager does not require calibrating the point spread function and has the capability to resolve depth and "see-through" opaque obstacles to image features being blocked, enabling broad applications in computational imaging.

Learning Phonotactics in a Differentiable Framework of Subregular Languages

Phonotactic constraints have been argued to beregular, meaning that they can be represented usingfinite-state automata (Heinz, 2018); furthermore, they have been argued to occupy a even more restrictedregion of the regular language class known as the subregular hierarchy (Rogers &amp; Pullum, 2011). Ourcontribution is to present a simple model of phonotactic learning from positive evidence. Our approach isbased on probabilistic finite-state automata (Vidal et al., 2005a,b). We study the model’s ability to induce localand nonlocal phonotactics from wordlist data, both with and without formal constraints on the automaton.In particular, we evaluate the ability of our learner to induce nonlocal phonotactic constraints from data ofNavajo and Quechua. Our work provides a framework in which different formal models of phonotactics canbe compared, and sheds light on the structural nature of phonological acquisition (Dai, 2021; Shibata &amp; Heinz,2019; Heinz &amp; Rogers, 2010, 2013).

A Study on Gear Defect Detection via Frequency Analysis Based on DNN

In this paper, we introduce a gear defect detection system using frequency analysis based on deep learning. The existing defect diagnosis systems using acoustic analysis use spectrogram, scalogram, and MFCC (Mel-Frequency Cepstral Coefficient) images as inputs to the convolutional neural network (CNN) model to diagnose defects. However, using visualized acoustic data as input to the CNN models requires a lot of computation time. Although computing power has improved, there is a situation in which a processor with low performance is used for reasons such as cost-effectiveness. In this paper, only the sums of frequency bands are used as input to the deep neural network (DNN) model to diagnose the gear fault. This system diagnoses the defects using only a few specific frequency bands, so it ignores unnecessary data and does not require high performance when diagnosing defects because it uses a relatively simple deep learning model for classification. We evaluate the performance of the proposed system through experiments and verify that real-time diagnosis of gears is possible compared to the CNN model. The result showed 95.5% accuracy for 1000 test data, and it took 18.48 ms, so that verified the capability of real-time diagnosis in a low-spec environment. The proposed system is expected to be effectively used to diagnose defects in various sound-based facilities at a low cost.

Quantitative Analysis of Anesthesia Recovery Time by Machine Learning Prediction Models

It is significant for anesthesiologists to have a precise grasp of the recovery time of the patient after anesthesia. Accurate prediction of anesthesia recovery time can support anesthesiologist decision-making during surgery to help reduce the risk of surgery in patients. However, effective models are not proposed to solve this problem for anesthesiologists. In this paper, we seek to find effective forecasting methods. First, we collect 1824 patient anesthesia data from the eye center and then performed data preprocessing. We extracted 85 variables to predict recovery time from anesthesia. Second, we extract anesthesia information between variables for prediction using machine learning methods, including Bayesian ridge, lightGBM, random forest, support vector regression, and extreme gradient boosting. We also design simple deep learning models as prediction models, including linear residual neural networks and jumping knowledge linear neural networks. Lastly, we perform a comparative experiment of the above methods on the dataset. The experiment demonstrates that the machine learning method performs better than the deep learning model mentioned above on a small number of samples. We find random forest and XGBoost are more efficient than other methods to extract information between variables on postoperative anesthesia recovery time.

AI-based prediction of new binding site and virtual screening for the discovery of novel P2X3 receptor antagonists

Artificial intelligence (AI) has been recognized as a powerful technique that can accelerate drug discovery during the hit compound identification step. However, most simple deep learning models have been used for naive pre-filtering as the prediction result cannot be interpreted. Recently, our group developed a new deep learning model (Highlight on Target Sequence; HoTS) that can predict binding regions in a target protein sequence based on patterns learned from interactions between a target protein sequence and a ligand. In this study, we searched for new binding regions of the P2X3 receptor (P2X3R) using HoTS, and suggested a novel putative binding site of P2X3R by a cavity search on the predicted binding regions. The novel putative binding site was employed to generate pharmacophore features, and combinations of pharmacophore features were validated as queries. Two separate virtual screenings using the optimized pharmacophore query Q12 with docking-based scoring and HoTS-based prediction of ligand interactions enabled the initial selection of the compound library for in vitro screening. The screening of each set of 500 compounds from the two approaches (HoTS interaction prediction and Pharmacophore-LibDock cascade) resulted in the identification of 10 (HoTS-1 – 10) and 6 compounds (PD-1 – 6) with low micromolar IC50 values. Remarkably, the hit rate was 10-fold higher than that from the previous random screening of 8364 compound library, and the chemical structures of all identified hit compounds were distinct from those of known P2X3R antagonists, indicating that novel chemical entities could be developed for P2X3R antagonists by targeting the binding site. Overall, this study suggests the discovery of a novel putative binding site for P2X3R using the AI deep learning protocol along with in silico MD simulation and experimental screening of targeted library compounds to successfully identify 16 unique and novel hit compounds. These results may accelerate the discovery of novel chemical-class drugs for P2X3R antagonists.

Pengaruh Model Pembelajaran Problem Based Learning Berbasis Experimen Sederhana dalam Pengenalan Sains Anak Usia Dini

Problem-solving and critical thinking in early childhood can be done by carrying out science introduction activities. This study aims to determine the effect of a simple experiment-based problem-based learning model in the introduction of early childhood science. The type of research used is a ranking pre-experimental design using an intact group comparison design. The class was chosen randomly, with 6 children in the control group and 6 children in the experimental group. Based on the results of the study, it was shown that the simple experiment-based problem-based learning model for early childhood could be done by recognizing liquid objects such as sinking, floating, soluble and insoluble, and the properties of liquids. The simple experiment-based problem-based learning model is very influential in the introduction of early childhood science, where children think critically and can form new ideas by solving a problem.

Introspection dynamics: a simple model of counterfactual learning in asymmetric games

Social behavior in human and animal populations can be studied as an evolutionary process. Individuals often make decisions between different strategies, and those strategies that yield a fitness advantage tend to spread. Traditionally, much work in evolutionary game theory considers symmetric games: individuals are assumed to have access to the same set of strategies, and they experience the same payoff consequences. As a result, they can learn more profitable strategies by imitation. However, interactions are oftentimes asymmetric. In that case, imitation may be infeasible (because individuals differ in the strategies they are able to use), or it may be undesirable (because individuals differ in their incentives to use a strategy). Here, we consider an alternative learning process which applies to arbitrary asymmetric games, introspection dynamics. According to this dynamics, individuals regularly compare their present strategy to a randomly chosen alternative strategy. If the alternative strategy yields a payoff advantage, it is more likely adopted. In this work, we formalize introspection dynamics for pairwise games. We derive simple and explicit formulas for the abundance of each strategy over time and apply these results to several well-known social dilemmas. In particular, for the volunteer’s timing dilemma, we show that the player with the lowest cooperation cost learns to cooperate without delay.

Priors Rule: When Do Malfeasance Revelations Help Or Hurt Incumbent Parties?

Abstract Effective policy-making requires that voters avoid electing malfeasant politicians. However, informing voters of incumbent malfeasance in corrupt contexts may not reduce incumbent support. As our simple learning model shows, electoral sanctioning is limited where voters already believed incumbents to be malfeasant, while information’s effect on turnout is non-monotonic in the magnitude of reported malfeasance. We conducted a field experiment in Mexico that informed voters about malfeasant mayoral spending before municipal elections, to test whether these Bayesian predictions apply in a developing context where many voters are poorly informed. Consistent with voter learning, the intervention increased incumbent vote share where voters possessed unfavorable prior beliefs and when audit reports caused voters to favorably update their posterior beliefs about the incumbent’s malfeasance. Furthermore, we find that low and, especially, high malfeasance revelations increased turnout, while less surprising information reduced turnout. These results suggest that improved governance requires greater transparency and citizen expectations.

Vision-Based American Sign Language Classification Approach via Deep Learning

Hearing-impaired is the disability of partial or total hearing loss that causes a significant problem for communication with other people in society. American Sign Language (ASL) is one of the sign languages that most commonly used language used by Hearing impaired communities to communicate with each other. In this paper, we proposed a simple deep learning model thataims to classify the American Sign Language letters as a step in a path for removing communication barriers that are related to disabilities.