Mixture of Experts (MoE) architectures increase large language model scalability, yet their performance depends on the router module that moves tokens to specialized experts. Bad routing can load imbalance and reduced accuracy. This project designed and implemented different router architectures within Transformer models to fix these limitations. We experimented with six distinct router variants Linear, Attention, Multi-Layer Perceptron (MLP), Hybrid, Hash, and our new MLP-Hadamard. We characterized these routers using BERT and the Qwen1.5-MoE model, looking at parameter efficiency, inference latency, routing entropy, and expert utilization patterns. Our evaluations showed distinct trade-offs: Linear routers offer speed, while MLP and Attention routers provide greater expressiveness. The MLP-Hadamard router shows a unique capability for structured, sparse routing. We successfully replaced and fine-tuned custom routers within the complex, quantized Qwen1.5-MoE model. This work provides a comparative analysis of MoE router designs and offers insights into optimizing their performance for efficient and effective large-scale model deployment.

This study introduces a framework that integrates nonlinear feature extraction, classification, and efficient optimization. First, kernel principal component analysis with a radial basis function kernel reduces dimensionality while preserving 95% of the variance. Second, a multilayer perceptron (MLP) learns to predict disease status. Finally, a modified multiprocessing genetic algorithm (MIGA) optimizes MLP hyperparameters in parallel over ten generations. We evaluated this approach on three datasets: the Wisconsin Diagnostic Breast Cancer dataset, the Parkinson's Telemonitoring dataset, and the chronic kidney disease dataset. The MLP tuned by the MIGA achieved the best accuracy of 99.12% for breast cancer, 94.87% for Parkinson's disease, and 100% for chronic kidney disease. These results outperform those of other methods, such as grid search, random search, and Bayesian optimization. Compared with a standard genetic algorithm, kernel PCA revealed nonlinear relationships that improved classification, and the MIGA's parallel fitness evaluations reduced the tuning time by approximately 60%. The genetic algorithm incurs high computational cost from sequential fitness evaluations, but our multiprocessing interface GA (MIGA) parallelizes this step, slashing the tuning time and steering the MLP toward the best accuracy score of 99.12%, 94.87%, and 100% for breast cancer, Parkinson's disease, and CKD, respectively.

This study bridges cognitive science and neural network design by examining whether artificial models exhibit human-like forgetting curves. Drawing upon Ebbinghaus' seminal work on memory decay and principles of spaced repetition, we propose a quantitative framework to measure information retention in neural networks. Our approach computes the recall probability by evaluating the similarity between a network's current hidden state and previously stored prototype representations. This retention metric facilitates the scheduling of review sessions, thereby mitigating catastrophic forgetting during deployment and enhancing training efficiency by prompting targeted reviews. Our experiments with Multi-Layer Perceptrons reveal human-like forgetting curves, with knowledge becoming increasingly robust through scheduled reviews. This alignment between neural network forgetting curves and established human memory models identifies neural networks as an architecture that naturally emulates human memory decay and can inform state-of-the-art continual learning algorithms.

Recent advancements in speech synthesis technologies have led to increasingly advanced spoofing attacks, posing significant challenges for automatic speaker verification systems. While systems based on self-supervised learning (SSL) models, particularly the XLSR-Conformer model, have demonstrated remarkable performance in synthetic speech detection, there remains room for architectural improvements. In this paper, we propose a novel approach that replaces the traditional Multi-Layer Perceptron in the XLSR-Conformer model with a Kolmogorov-Arnold Network (KAN), a novel architecture based on the Kolmogorov-Arnold representation theorem. Our results on ASVspoof2021 demonstrate that integrating KAN into the SSL-based models can improve the performance by 60.55% relatively on LA and DF sets, further achieving 0.70% EER on the 21LA set. These findings suggest that incorporating KAN into SSL-based models is a promising direction for advances in synthetic speech detection.

The high computational complexity and increasing parameter counts of deep neural networks pose significant challenges for deployment in resource-constrained environments, such as edge devices or real-time systems. To address this, we propose a parameter-efficient neural architecture where neurons are embedded in Euclidean space. During training, their positions are optimized and synaptic weights are determined as the inverse of the spatial distance between connected neurons. These distance-dependent wiring rules replace traditional learnable weight matrices and significantly reduce the number of parameters while introducing a biologically inspired inductive bias: connection strength decreases with spatial distance, reflecting the brain's embedding in three-dimensional space where connections tend to minimize wiring length. We validate this approach for both multi-layer perceptrons and spiking neural networks. Through a series of experiments, we demonstrate that these spatially embedded neural networks achieve a performance competitive with conventional architectures on the MNIST dataset. Additionally, the models maintain performance even at pruning rates exceeding 80% sparsity, outperforming traditional networks with the same number of parameters under similar conditions. Finally, the spatial embedding framework offers an intuitive visualization of the network structure.

Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias does not present in conventional GNNs. Unlike prior art in machine learning over DAGs, DCN builds on formal convolutional operations that admit spectral-domain representations. We further propose the Parallel DCN (PDCN), a model that feeds input DAG signals to a parallel bank of causal graph-shift operators and processes these DAG-aware features using a shared multilayer perceptron. This way, PDCN decouples model complexity from graph size while maintaining satisfactory predictive performance. The architectures' permutation equivariance and expressive power properties are also established. Comprehensive numerical tests across several tasks, datasets, and experimental conditions demonstrate that (P)DCN compares favorably with state-of-the-art baselines in terms of accuracy, robustness, and computational efficiency. These results position (P)DCN as a viable framework for deep learning from DAG-structured data that is designed from first (graph) signal processing principles.

Variational Quantum Circuits (VQCs) offer a novel pathway for quantum machine learning, yet their practical application is hindered by inherent limitations such as constrained linear expressivity, optimization challenges, and acute sensitivity to quantum hardware noise. This work introduces VQC-MLPNet, a scalable and robust hybrid quantum-classical architecture designed to overcome these obstacles. By innovatively employing quantum circuits to dynamically generate parameters for classical Multi-Layer Perceptrons (MLPs) via amplitude encoding and parameterized quantum operations, VQC-MLPNet substantially expands representation capabilities and augments training stability. We provide rigorous theoretical guarantees via statistical learning techniques and Neural Tangent Kernel analysis, explicitly deriving upper bounds on approximation, uniform deviation, and optimization errors. These theoretical insights demonstrate exponential improvements in representation capacity relative to quantum circuit depth and the number of qubits, providing clear computational advantages over standalone quantum circuits and existing hybrid quantum architectures. Our theoretical claims are empirically corroborated through extensive experiments, including classifying semiconductor quantum-dot charge states and predicting genomic transcription factor binding sites, demonstrating resilient performance even under realistic IBM quantum noise simulations. This research establishes a theoretically sound and practically robust framework, advancing the frontiers of quantum-enhanced learning for unconventional computing paradigms in the Noisy Intermediate-Scale Quantum era and beyond.

This study conducts an empirical examination of MLP networks investigated through a rigorous methodical experimentation process involving three diverse datasets: TinyFace, Heart Disease, and Iris. Study Overview: The study includes three key methods: a) a baseline training using the default settings for the Multi-Layer Perceptron (MLP), b) feature selection using Genetic Algorithm (GA) based refinement c) Principal Component Analysis (PCA) based dimension reduction. The results show important information on how such techniques affect performance. While PCA had showed benefits in low-dimensional and noise-free datasets GA consistently increased accuracy in complex datasets by accurately identifying critical features. Comparison reveals that feature selection and dimensionality reduction play interdependent roles in enhancing MLP performance. The study contributes to the literature on feature engineering and neural network parameter optimization, offering practical guidelines for a wide range of machine learning tasks

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding and generation by integrating visual and textual information. While instruction tuning and parameter-efficient fine-tuning methods have substantially improved the generalization of VLMs, most existing approaches rely on centralized training, posing challenges for deployment in domains with strict privacy requirements like healthcare. Recent efforts have introduced Federated Learning (FL) into VLM fine-tuning to address these privacy concerns, yet comprehensive benchmarks for evaluating federated fine-tuning strategies, model architectures, and task generalization remain lacking. In this work, we present \textbf{FedVLMBench}, the first systematic benchmark for federated fine-tuning of VLMs. FedVLMBench integrates two mainstream VLM architectures (encoder-based and encoder-free), four fine-tuning strategies, five FL algorithms, six multimodal datasets spanning four cross-domain single-task scenarios and two cross-domain multitask settings, covering four distinct downstream task categories. Through extensive experiments, we uncover key insights into the interplay between VLM architectures, fine-tuning strategies, data heterogeneity, and multi-task federated optimization. Notably, we find that a 2-layer multilayer perceptron (MLP) connector with concurrent connector and LLM tuning emerges as the optimal configuration for encoder-based VLMs in FL. Furthermore, current FL methods exhibit significantly higher sensitivity to data heterogeneity in vision-centric tasks than text-centric ones, across both encoder-free and encoder-based VLM architectures. Our benchmark provides essential tools, datasets, and empirical guidance for the research community, offering a standardized platform to advance privacy-preserving, federated training of multimodal foundation models.

Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and memory overheads has become increasingly urgent. Sparsity has emerged as a leading approach in this area. The robustness of sparse Multi-layer Perceptrons (MLPs) for supervised feature selection, along with the application of Sparse Evolutionary Training (SET), illustrates the feasibility of reducing computational costs without compromising accuracy. Moreover, it is believed that the SET algorithm can still be improved through a structural optimization method called motif-based optimization, with potential efficiency gains exceeding 40% and a performance decline of under 4%. This research investigates whether the structural optimization of Sparse Evolutionary Training applied to Multi-layer Perceptrons (SET-MLP) can enhance performance and to what extent this improvement can be achieved.