القائمة
Supervised Memory Training (SMT) methodology for parallel RNN pretraining without backpropagation through time.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/hiyenwong/ai_collection --skill supervised-memory-trainingيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.
Physics-aware end-to-end deep reinforcement learning methodology for quadcopter control with actuator dynamics modeling.
Reinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | supervised-memory-training |
| category | neuroscience |
| description | Supervised Memory Training (SMT) methodology for parallel RNN pretraining without backpropagation through time. |
| activation | RNN training, supervised memory, parallel training, predictive state, memory transition, BPTT replacement |
Supervised Memory Training (SMT) methodology for parallel RNN pretraining without backpropagation through time. Based on arXiv: 2606.06479.
Supervised Memory Training (SMT) trains nonlinear RNNs without recurrent credit propagation by reducing to supervised learning on one-step memory transition labels. SMT acquires memory labels by training a Transformer-based encoder on a predictive state objective, retaining only information from the past necessary to predict the future. Decouples what to remember from how to update memory. Enables time-parallel RNN training with stable O(1) length gradient path without unrolling the RNN.
Apply this methodology when analyzing or implementing the described approach.
Compare against baseline approaches to validate improvements.
Read the paper abstract and identify the key methodological contribution.
Determine if the methodology applies to the current problem domain.
Either apply the methodology directly or use it as a comparison baseline.
