3 مستودعات
Multi-task learning architectures that share bottom layers across multiple prediction objectives to learn from related tasks simultaneously.
Distinct from Multi-Task Learning Models: Distinct from Multi-Task Learning Models: specifically focuses on the shared-bottom architecture pattern rather than general multi-task sequence models.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Shared-Bottom Architectures. Refine with filters or upvote what's useful.
DeepCTR is a specialized software framework and deep learning model library designed for predicting click-through rates and implementing recommendation systems. It provides a suite of tabular data models and architectures tailored for binary classification and sparse feature processing. The framework includes dedicated toolkits for multi-task learning and sequential interest modeling. It allows for the simultaneous estimation of multiple related targets through shared-bottom and gated expert neural networks, while capturing evolving user behavior using attention mechanisms and transformers.
Implements shared-bottom architectures to estimate multiple related targets using shared neural representations.
Sapiens هو نموذج رؤية بشرية عالي الدقة مصمم لمهام رؤية الكمبيوتر التي تركز على الإنسان بدقة عالية. يعمل كمجموعة من الأدوات لتقدير وضعية الإنسان، والعمق، وهندسة السطح. يستخدم المشروع هيكل vision transformer لأداء مهام متعددة من خلال مشفر مشترك. تتيح هذه البنية التنبؤ المتزامن بالهياكل الهيكلية، ومواقع المفاصل، والمسافة بين الكاميرا والموضوع البشري. تغطي قدرات النموذج تجزئة أجزاء جسم الإنسان لعزل المناطق التشريحية عن الخلفيات والتنبؤ بوضع السطح لاستعادة التفاصيل الهندسية ثلاثية الأبعاد من الصور ثنائية الأبعاد. يتم دعم هذه المهام من خلال إطار عمل للتعلم متعدد المهام يستخدم الانحدار على مستوى البكسل وقناع التجزئة الدلالي.
Uses a shared-bottom architecture to extract features for multiple specialized human-centric output heads.
DeepCTR-Torch is a deep learning library for building click-through rate prediction models. It provides a modular framework for assembling custom prediction architectures from pre-built core, interaction, and sequence layers, enabling the construction of deep neural networks that estimate click probability from user behavior data. The library specializes in feature interaction modeling, offering components for learning low-order, high-order, and adaptive-order feature crosses. It supports multi-task learning for predicting multiple objectives simultaneously, such as click and conversion rates
Shares bottom layers across multiple prediction objectives to learn click and conversion rates simultaneously.