https://sriharsha-paladugula.github.io/SriHarsha Paladugulablog, sriharsha, harsha, paladugula, github 2025-12-12T05:54:50+00:00 SriHarsha Paladugula https://sriharsha-paladugula.github.io/ Jekyll © 2025 SriHarsha Paladugula /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png Neural Architecture Search Part 5: Hardware-Aware NAS and Co-Design2025-08-04T00:00:00+00:00 2025-12-11T15:02:18+00:00 https://sriharsha-paladugula.github.io/posts/Neural-Architecture-Search-Part5-Hardware-Codesign/ SriHarsha Paladugula We’ve traveled through NAS theory, search strategies, real-world applications, and efficient estimation techniques. But we’ve been operating under a hidden assumption: we optimize architectures for a generic “hardware” target. In reality, neural networks don’t run on abstract computers—they run on specific devices: GPUs, CPUs, mobile phones, TPUs, and specialized edge accelerators. Each has un... Neural Architecture Search Part 4: Efficient Estimation Strategies2025-07-30T00:00:00+00:00 2025-12-11T15:02:18+00:00 https://sriharsha-paladugula.github.io/posts/Neural-Architecture-Search-Part4-Efficient-Estimation/ SriHarsha Paladugula One of the biggest challenges in Neural Architecture Search is cost: evaluating thousands of candidate architectures by training them all from scratch takes months on supercomputers. In Part 3, we learned about the real-world impact of NAS, but we glossed over a critical question: how do we actually afford to run NAS? In this part, we’ll explore the efficiency problem and discover clever techn... Neural Architecture Search Part 3: Applications and Real-World Impact2025-07-25T00:00:00+00:00 2025-12-11T15:02:18+00:00 https://sriharsha-paladugula.github.io/posts/Neural-Architecture-Search-Part3-Applications/ SriHarsha Paladugula In Part 1, we learned the foundations of Neural Architecture Search, and in Part 2, we explored search spaces and strategies. Now comes the exciting part: what have we actually discovered using NAS? In this final part, we’ll explore real-world applications and see how NAS has transformed deep learning in practice. From Theory to Practice NAS started as an academic pursuit, but it has rapidly ... Neural Architecture Search Part 2: Search Spaces and Strategies2025-07-20T00:00:00+00:00 2025-12-11T15:02:18+00:00 https://sriharsha-paladugula.github.io/posts/Neural-Architecture-Search-Part2-Search-Strategies/ SriHarsha Paladugula Now that we understand the foundations of neural architecture search, we can tackle the critical question: how do we actually search for good architectures? In this part, we’ll explore search spaces—the universe of possible architectures—and the strategies we can use to navigate them. What is Neural Architecture Search? Neural Architecture Search is an automated approach to discovering neural... Neural Architecture Search Part 1: Foundations and Building Blocks2025-07-15T00:00:00+00:00 2025-12-11T15:02:18+00:00 https://sriharsha-paladugula.github.io/posts/Neural-Architecture-Search-Part1-Foundations/ SriHarsha Paladugula Neural Architecture Search (NAS) is one of the most exciting developments in deep learning—a technique that automates the design of neural network architectures rather than relying on human engineers to manually craft them. In this first part, we’ll explore the foundations, understand why NAS matters, and learn about the building blocks that form the basis of modern neural networks. The Challe...