2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Yayın Adaptive locally connected recurrent unit (ALCRU)(Springer Science and Business Media Deutschland GmbH, 2025-07-03) Özçelik, Şuayb Talha; Tek, Faik BorayResearch has shown that adaptive locally connected neurons outperform their fully connected (dense) counterparts, motivating this study on the development of the Adaptive Locally Connected Recurrent Unit (ALCRU). ALCRU modifies the Simple Recurrent Neuron Model (SimpleRNN) by incorporating spatial coordinate spaces for input and hidden state vectors, facilitating the learning of parametric local receptive fields. These modifications add four trainable parameters per neuron, resulting in a minor increase in computational complexity. ALCRU is implemented using standard frameworks and trained with back-propagation-based optimizers. We evaluate the performance of ALCRU using diverse benchmark datasets, including IMDb for sentiment analysis, AdditionRNN for sequence modelling, and the Weather dataset for time-series forecasting. Results show that ALCRU achieves accuracy and loss metrics comparable to GRU and LSTM while consistently outperforming SimpleRNN. In particular, experiments with longer sequence lengths on AdditionRNN and increased input dimensions on IMDb highlight ALCRU’s superior scalability and efficiency in processing complex data sequences. In terms of computational efficiency, ALCRU demonstrates a considerable speed advantage over gated models like LSTM and GRU, though it is slower than SimpleRNN. These findings suggest that adaptive local connectivity enhances both the accuracy and efficiency of recurrent neural networks, offering a promising alternative to standard architectures.Yayın From policy to practice: a sector-agnostic operational framework for post-quantum cryptography transition(Institute of Electrical and Electronics Engineers Inc., 2026-03-02) Birgin, Berat; Çeliktaş, BarışThe pace of quantum computing development necessitates not only the adoption of post-quantum cryptographic algorithms, but also the establishment of an executable and auditable institutional transition process. Although guidance documents published by the National Institute of Standards and Technology (NIST) and roadmaps proposed by the Post-Quantum Cryptography Coalition (PQCC) articulate strategic objectives, they largely remain procedural constructs lacking a concrete operational execution model. This paper presents an industry-neutral operational framework that translates policy-level post-quantum cryptography (PQC) guidance into deterministic, proof-producing process flows encompassing cryptographic asset discovery, classification, risk modeling, algorithm selection, deployment, monitoring, and governance enforcement. Central to the framework is a deterministic Quantum Risk Scoring (QRS) function, calibrated using the Analytical Hierarchy Process (AHP), which enables reproducible asset prioritization and policy-driven enforcement decisions. Framework executability is further strengthened through cryptography-aware continuous integration/continuous deployment (CI/CD) validation gates and downgrade protection mechanisms, ensuring the generation of verifiable and immutable audit artifacts. A scenario-based operational validation, implemented using open-source toolchains, demonstrates the framework’s operability, auditability, and governance alignment without relying on empirical cryptographic performance benchmarks, confirming that PQC transition can be operationalized as a verifiable lifecycle process bridging policy guidance with enforceable technical actions. Rather than introducing new cryptographic primitives, this work formalizes PQC transition as an operational systems-engineering problem centered on governance-enforced execution and lifecycle verifiability.
