2: How AI Works (Rule-Based vs. Machine Learning, Feature Extraction, Data Quality and Quantity, Neural Networks) — البرمجة والذكاء الاصطناعي الصف الثاني الثانوي لغات

الدرس ده من وحدة «Principles of Algorithms and Computational Thinking» فى مادة البرمجة والذكاء الاصطناعي لـالصف الثاني الثانوي لغات على منصة دروسات.

الدرس متاح بالاشتراك: ترم كامل أو المادة لوحدها.

ملخص الدرس

This lesson demystifies how AI systems operate under the hood. It contrasts classical rule-based deterministic programming with probabilistic Machine Learning. It explores feature extraction and representation, the critical dependency of AI performance on training data quality and volume, and details the foundational architecture of Artificial Neural Networks (input, hidden, and output layers with synaptic weights).

هتتعلم إيه فى الدرس ده

• Rule-based systems require humans to write explicit deterministic rules.
• Machine Learning algorithms learn statistical patterns directly from large training datasets.
• Features are distinct measurable properties used to classify and predict data.
• Deep learning automates feature extraction through multilayer neural architectures.
• Model accuracy strictly relies on massive, diverse, accurately labeled training data.
• Neural networks mimic biological neurons via input, hidden, and output layers with adjustable weights.