无需编程，深入神经架构搜索(NAS)与自动化机器学习(AutoML)理论。从数学基石到高维嵌入，解构强化学习与贝叶斯优化，助你构建系统化架构设计心智模型。
原始标题：Neural Architecture Search (NAS) & Automated ML (AutoML)
本课程是一门完全免编程的纯理论高阶课程，专注于解构神经架构搜索（NAS）与自动化机器学习（AutoML）的底层黑盒。课程从线性代数、凸优化等数学基石出发，深度剖析机器学习的偏置-方差限界与梯度传播模型，并进一步探索高维嵌入几何学。在核心系统设计层面，学员将彻底解构强化学习、进化算法和贝叶斯优化在拓扑搜索中的应用范式，并在资源、成本与延迟之间建立深刻的架构权衡思维。通过将离散网络连续化松弛、超网权重共享等前沿数据映射理论转化为具象的系统框架，帮助无编程背景的技术爱好者、架构师及科研新手跳出代码细节，从宏观维度建立起一套系统化、多维度的自主系统设计图谱与战略 mental model（心智模型）。
Published 7/2026
Created by Bhushan S
MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 49 Lectures ( 4h 25m ) | Size: 3.4 GB
A theoretical study of how systems autonomously discover optimal neural topologies, hyperparameters, and process.
What you’ll learn
⚡ Understand key concepts in Mathematical Foundations: Linear Algebra & Optimization.
⚡ Understand key concepts in Machine Learning Paradigms & Bias-Variance Bounds.
⚡ Understand key concepts in Deep Neural Networks & Gradient Propagation Models.
⚡ Understand key concepts in Natural Language Processing & Embedding Geometries.
Requirements
❗ No coding experience is required. We focus entirely on system design and core theoretical concepts.
❗ A basic interest in technology systems, algorithms, or computer science architecture.
❗ No special software or local development environment setup is needed.
DescriptionThis course contains the use of artificial intelligence.
Note: Artificial intelligence tools were used to assist with content organization, outlining, and structural generation to enhance your learning experience. However, all course materials have been extensively reviewed, edited, and expanded with unique instructor insights and real-world expertise to ensure accuracy and the highest quality standards.
Unlock the deep theoretical foundations of Neural Architecture Search (NAS) & Automated Machine Learning (AutoML) — completely programming-free.
In today’s fast-evolving technology landscape, writing code is only a fraction of the challenge. The real value lies in understanding system design, core mathematical constraints, architectural patterns, and structural trade-offs. This course is built to build your conceptual frameworks from the ground up, avoiding coding syntaxes and focusing on the underlying mental models.
What you will master in this course
✨System Paradigms: Deep-dive into the underlying structures of Reinforcement Learning Search Spaces, Evolutionary Algorithms, and Bayesian Optimization.
✨Architectural Trade-offs: Learn how decisions influence latency, cost, memory, and scalability.
✨Structural Flow: Walk through theoretical operations and data mappings.
✨Governance & Best Practices: Study governing patterns to design resilient, production-ready systems.
Who this course is for
⭐ Data Science Leads, ML Researchers, Automation Architects
百度网盘下载：
