بعد أكاديمية كاوست
As of October 2026, Bandar is studying at King Saud University, with graduation expected in 2027. Bandar completed the DeepLearning.AI course on Linear Algebra for Machine Learning and Data Science in September 2026.
المشروع الصيفي
تخصص الذكاء الاصطناعي · دفعة 2026
How to Regularize Autoencoders for Real-World Engineering Data? A Systematic Study Across Data Regimes and Latent Bottlenecks
We benchmark ten autoencoder regularization techniques — Vanilla, L1, L2, Contractive, Sparse, VAE, IRMAE, LoRAE, RRAE, and Denoising — on four synthetic PDE datasets of increasing difficulty: a translating Gaussian bump, thin-plate deflection, Gray–Scott reaction–diffusion, and a multi-channel shallow-water wave. All techniques share one convolutional backbone, one reconstruction loss, and one training budget, so differences come only from the penalty. We evaluate with an FID-style metric and latent-interpolation quality across multiple seeds, plus a per-technique hyperparameter ablation that separates real gains from seed noise. The outcome is a practical guide to regularizer choice for data-scarce engineering problems.
مع أكاديمية كاوست
- دفعة 2026
جامعة الملك خالد · المدرسة الصيفية للذكاء الاصطناعي
هل تريد تحديث بياناتك أو حذفها؟ تواصل معنا.