Search Results (24)

Predicting the motion of handwritten digits in video sequences is challenging due to complex spatiotemporal dependencies, variable writing styles, and the need to preserve fine-grained visual details—all of which are essential for real-time handwriting recognition and digital learning applications. In this context, our study aims to develop a robust predictive framework that can accurately forecast digit trajectories while preserving structural integrity. To address these challenges, we propose a novel video prediction architecture integrating ConvCARU with a modified DCGAN to effectively separate the background from the foreground. This ensures the enhanced extraction and preservation of spatial and temporal features through convolution-based gating and adaptive fusion mechanisms. Based on extensive experiments conducted on the MNIST dataset, which comprises 70 K pixel images, our approach achieves an SSIM of 0.901 and a PSNR of 29.31 dB. This reflects a statistically significant improvement in PSNR of +0.20 dB (p < 0.05) compared to current state-of-the-art models, thus demonstrating its superior capability in maintaining consistent structural fidelity in predicted video frames. Furthermore, our framework performs better in terms of computational efficiency, with lower memory consumption compared to most other approaches. This underscores its practicality for deployment in real-time, resource-constrained applications. These promising results consequently validate the effectiveness of our integrated ConvCARU–DCGAN approach in capturing fine-grained spatiotemporal dependencies, positioning it as a compelling solution for enhancing video-based handwriting recognition and sequence forecasting. This paves the way for its adoption in diverse applications requiring high-resolution, efficient motion prediction. Full article

Brain-inspired neuromorphic computing is expected to overcome the von Neumann bottleneck by eliminating the memory wall between processing and memory units. Nevertheless, critical challenges persist in synaptic device implementation, particularly regarding nonlinear/asymmetric conductance modulation and multilevel conductance states, which substantially impede the realization of high-performance neuromorphic hardware. This study demonstrates a novel advancement in photonic–electronic modulated synaptic devices through the development of an amorphous indium–gallium–zinc oxide (a-IGZO) synaptic transistor. The device demonstrates biological synaptic functionalities, including excitatory/inhibitory post-synaptic currents (EPSCs/IPSCs) and spike-timing-dependent plasticity, while achieving excellent conductance modulation characteristics (nonlinearity of 0.0095/−0.0115 and asymmetric ratio of 0.247) and successfully implementing Pavlovian associative learning paradigms. Notably, systematic neural network simulations employing the experimental parameters reveal a 93.8% recognition accuracy on the MNIST handwritten digit dataset. The a-IGZO synaptic transistor with photonic–electronic co-modulation serves as a potential critical building block for constructing neuromorphic architectures with human-brain efficiency. Full article

Video location prediction for handwritten digits presents unique challenges in computer vision due to the complex spatiotemporal dependencies and the need to maintain digit legibility across predicted frames, while existing deep learning-based video prediction models have shown promise, they often struggle with preserving local details and typically achieve clear predictions for only a limited number of frames. In this paper, we present a novel video location prediction model based on Convolutional Gated Recurrent Units (ConvGRU) that specifically addresses these challenges in the context of handwritten digit sequences. Our approach introduces three key innovations. Firstly, we introduce a specialized decoupling model using modified Generative Adversarial Networks (GANs) that effectively separates background and foreground information, significantly improving prediction accuracy. Secondly, we introduce an enhanced ConvGRU architecture that replaces traditional linear operations with convolutional operations in the gating mechanism, substantially reducing spatiotemporal information loss. Finally, we introduce an optimized parameter-tuning strategy that ensures continuous feature transmission while maintaining computational efficiency. Extensive experiments on both the MNIST dataset and custom mobile datasets demonstrate the effectiveness of our approach. Our model achieves a structural similarity index of 0.913 between predicted and actual sequences, surpassing current state-of-the-art methods by 1.2%. Furthermore, we demonstrate superior performance in long-term prediction stability, with consistent accuracy maintained across extended sequences. Notably, our model reduces training time by 9.5% compared to existing approaches while maintaining higher prediction accuracy. These results establish new benchmarks for handwritten digit video prediction and provide practical solutions for real-world applications in digital education, document processing, and real-time handwriting recognition systems. Full article

Binary neural networks (BNNs) that use 1-bit weights and activations have garnered interest as extreme quantization provides low power dissipation. By implementing BNNs as computation-in-memory (CIM), which computes multiplication and accumulations on memory arrays in an analog fashion, namely, analog CIM, we can further improve the energy efficiency to process neural networks. However, analog CIMs are susceptible to process variation, which refers to the variability in manufacturing that causes fluctuations in the electrical properties of transistors, resulting in significant degradation in BNN accuracy. Our Monte Carlo simulations demonstrate that in an SRAM-based analog CIM implementing the VGG-9 BNN model, the classification accuracy on the CIFAR-10 image dataset is degraded to below 50% under process variations in a 28 nm FD-SOI technology. To overcome this problem, we present a variation-aware BNN framework. The proposed framework is developed for SRAM-based BNN CIMs since SRAM is most widely used as on-chip memory; however, it is easily extensible to BNN CIMs based on other memories. Our extensive experimental results demonstrate that under process variation of 28 nm FD-SOI, with an SRAM array size of $128\times 128$, our framework significantly enhances classification accuracies on both the MNIST hand-written digit dataset and the CIFAR-10 image dataset. Specifically, for the CONVNET BNN model on MNIST, accuracy improves from 60.24% to 92.33%, while for the VGG-9 BNN model on CIFAR-10, accuracy increases from 45.23% to 78.22%. Full article

With the advent of increasingly powerful machine learning algorithms and the ability to rapidly obtain accurate aerodynamic performance data, there has been a steady rise in the use of algorithms for automated aerodynamic design optimisation. However, long training times, high-dimensional design spaces and rapid geometry alteration pose barriers to this becoming an efficient and worthwhile process. The variational autoencoder (VAE) is a probabilistic generative model capable of learning a low-dimensional representation of high-dimensional input data. Despite their impressive power, VAEs suffer from several issues, resulting in poor model performance and limiting optimisation capability. Several approaches have been proposed in attempts to fix these issues. This study combines the approaches of loss function modification with evolutionary hyperparameter tuning, introducing a new self-adaptive evolutionary info variational autoencoder (SA-eInfoVAE). The proposed model is validated against previous models on the MNIST handwritten digits dataset, assessing the total model performance. The proposed model is then applied to an aircraft image dataset to assess the applicability and complications involved with complex datasets such as those used for aerodynamic design optimisation. The results obtained on the MNIST dataset show improved inference in conjunction with increased generative and reconstructive performance. This is validated through a thorough comparison against baseline models, including quantitative metrics reconstruction error, loss function calculation and disentanglement percentage. A number of qualitative image plots provide further comparison of the generative and reconstructive performance, as well as the strength of latent encodings. Furthermore, the results on the aircraft image dataset show the proposed model can produce high-quality reconstructions and latent encodings. The analysis suggests, given a high-quality dataset and optimal network structure, the proposed model is capable of outperforming the current VAE models, reducing the training time cost and improving the quality of automated aerodynamic design optimisation. Full article

Addressing the issues of prolonged training times and low recognition rates in large model applications, this paper proposes a weight training method based on entropy gain for weight initialization and dynamic adjustment of the learning rate using the multilayer perceptron (MLP) model as an example. Initially, entropy gain was used to replace random initial values for weight initialization. Subsequently, an incremental learning rate strategy was employed for weight updates. The model was trained and validated using the MNIST handwritten digit dataset. The experimental results showed that, compared to random initialization, the proposed initialization method improves training effectiveness by 39.8% and increases the maximum recognition accuracy by 8.9%, demonstrating the feasibility of this method in large model applications. Full article

Recent advancements in cognitive neuroscience, particularly in electroencephalogram (EEG) signal processing, image generation, and brain–computer interfaces (BCIs), have opened up new avenues for research. This study introduces a novel framework, Bridging Artificial Intelligence and Neurological Signals (BRAINS), which leverages the power of artificial intelligence (AI) to extract meaningful information from EEG signals and generate images. The BRAINS framework addresses the limitations of traditional EEG analysis techniques, which struggle with nonstationary signals, spectral estimation, and noise sensitivity. Instead, BRAINS employs Long Short-Term Memory (LSTM) networks and contrastive learning, which effectively handle time-series EEG data and recognize intrinsic connections and patterns. The study utilizes the MNIST dataset of handwritten digits as stimuli in EEG experiments, allowing for diverse yet controlled stimuli. The data collected are then processed through an LSTM-based network, employing contrastive learning and extracting complex features from EEG data. These features are fed into an image generator model, producing images as close to the original stimuli as possible. This study demonstrates the potential of integrating AI and EEG technology, offering promising implications for the future of brain–computer interfaces. Full article

In the era of big data, millions and millions of data are generated every second by different types of devices. Training machine-learning models with these data has become increasingly common. However, the data used for training are often sensitive and may contain information such as medical, banking, or consumer records, for example. These data can cause problems in people’s lives if they are leaked and also incur sanctions for companies that leak personal information for any reason. In this context, Federated Learning emerges as a solution to the privacy of personal data. However, even when only the gradients of the local models are shared with the central server, some attacks can reconstruct user data, allowing a malicious server to violate the FL principle, which is to ensure the privacy of local data. We propose a secure aggregation protocol for Decentralized Federated Learning, which does not require a central server to orchestrate the aggregation process. To achieve this, we combined a Multi-Secret-Sharing scheme with a Dining Cryptographers Network. We validate the proposed protocol in simulations using the MNIST handwritten digits dataset. This protocol achieves results comparable to Federated Learning with the FedAvg protocol while adding a layer of privacy to the models. Furthermore, it obtains a timing performance that does not significantly affect the total training time, unlike protocols that use Homomorphic Encryption. Full article

We investigate the utility of side information in the context of machine learning and, in particular, in supervised neural networks. Side information can be viewed as expert knowledge, additional to the input, that may come from a knowledge base. Unlike other approaches, our formalism can be used by a machine learning algorithm not only during training but also during testing. Moreover, the proposed approach is flexible as it caters for different formats of side information, and we do not constrain the side information to be fed into the input layer of the network. A formalism is presented based on the difference between the neural network loss without and with side information, stating that it is useful when adding side information reduces the loss during the test phase. As a proof of concept we provide experimental results for two datasets, the MNIST dataset of handwritten digits and the House Price prediction dataset. For the experiments we used feedforward neural networks containing two hidden layers, as well as a softmax output layer. For both datasets, side information is shown to be useful in that it improves the classification accuracy significantly. Full article

In this paper, a novel feature generator framework is proposed for handwritten digit classification. The proposed framework includes a two-stage cascaded feature generator. The first stage is based on principal component analysis (PCA), which generates projected data on principal components as features. The second one is constructed by a partially trained neural network (PTNN), which uses projected data as inputs and generates hidden layer outputs as features. The features obtained from the PCA and PTNN-based feature generator are tested on the MNIST and USPS datasets designed for handwritten digit sets. Minimum distance classifier (MDC) and support vector machine (SVM) methods are exploited as classifiers for the obtained features in association with this framework. The performance evaluation results show that the proposed framework outperforms the state-of-the-art techniques and achieves accuracies of 99.9815% and 99.9863% on the MNIST and USPS datasets, respectively. The results also show that the proposed framework achieves almost perfect accuracies, even with significantly small training data sizes. Full article

Handwritten digit recognition has been used in many consumer electronic devices for a long time. However, we found that the recognition system used in current consumer electronics is sensitive to image or character rotations. To address this problem, this study builds a low-cost and light computation consumption handwritten digit recognition system. A Principal Component Analysis (PCA)-based logistic regression classifier is presented, which is able to provide a certain degree of robustness in the digit subject to rotations. To validate the effectiveness of the developed image recognition algorithm, the popular MNIST dataset is used to conduct performance evaluations. Compared to other popular classifiers installed in MATLAB, the proposed method is able to achieve better prediction results with a smaller model size, which is 18.5% better than the traditional logistic regression. Finally, real-time experiments are conducted to verify the efficiency of the presented method, showing that the proposed system is successfully able to classify the rotated handwritten digit. Full article

A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space. Full article

Advanced artificial intelligence (AI) techniques have led to significant developments in optical character recognition (OCR) technologies. OCR applications, using AI techniques for transforming images of typed text, handwritten text, or other forms of text into machine-encoded text, provide a fair degree of accuracy for general text. However, even after decades of intensive research, creating OCR with human-like abilities has remained evasive. One of the challenges has been that OCR models trained on general text do not perform well on localized or personalized handwritten text due to differences in the writing style of alphabets and digits. This study aims to discuss the steps needed to create an adaptive framework for OCR models, with the intent of exploring a reasonable method to customize an OCR solution for a unique dataset of English language numerical digits were developed for this study. We develop a digit recognizer by training our model on the MNIST dataset with a convolutional neural network and contrast it with multiple models trained on combinations of the MNIST and custom digits. Using our methods, we observed results comparable with the baseline and provided recommendations for improving OCR accuracy for localized or personalized handwritten text. This study also provides an alternative perspective to generating data using conventional methods, which can serve as a gold standard for custom data augmentation to help address the challenges of scarce data and data imbalance. Full article

In recent years, various deep neural networks with different learning paradigms have been widely employed in various applications, including medical diagnosis, image analysis, self-driving vehicles and others. The activation functions employed in deep neural networks have a huge impact on the training model and the reliability of the model. The Rectified Linear Unit (ReLU) has recently emerged as the most popular and extensively utilized activation function. ReLU has some flaws, such as the fact that it is only active when the units are positive during back-propagation and zero otherwise. This causes neurons to die (dying ReLU) and a shift in bias. However, unlike ReLU activation functions, Swish activation functions do not remain stable or move in a single direction. This research proposes a new activation function named NIPUNA for deep neural networks. We test this activation by training on customized convolutional neural networks (CCNN). On benchmark datasets (Fashion MNIST images of clothes, MNIST dataset of handwritten digits), the contributions are examined and compared to various activation functions. The proposed activation function can outperform traditional activation functions. Full article

Memristors have been considered to be more efficient than traditional Complementary Metal Oxide Semiconductor (CMOS) devices in implementing artificial synapses, which are fundamental yet very critical components of neurons as well as neural networks. Compared with inorganic counterparts, organic memristors have many advantages, including low-cost, easy manufacture, high mechanical flexibility, and biocompatibility, making them applicable in more scenarios. Here, we present an organic memristor based on an ethyl viologen diperchlorate [EV(ClO₄)]₂/triphenylamine-containing polymer (BTPA-F) redox system. The device with bilayer structure organic materials as the resistive switching layer (RSL) exhibits memristive behaviors and excellent long-term synaptic plasticity. Additionally, the device’s conductance states can be precisely modulated by consecutively applying voltage pulses between the top and bottom electrodes. A three-layer perception neural network with in situ computing enabled was then constructed utilizing the proposed memristor and trained on the basis of the device’s synaptic plasticity characteristics and conductance modulation rules. Recognition accuracies of 97.3% and 90% were achieved, respectively, for the raw and 20% noisy handwritten digits images from the Modified National Institute of Standards and Technology (MNIST) dataset, demonstrating the feasibility and applicability of implementing neuromorphic computing applications utilizing the proposed organic memristor. Full article