819: PyTorch: From Zero to Hero — with Luka Anicin

Topics covered
Popular Clips
Questions from this episode
- Asked by 45 people
Episode Highlights
Early Learning
Luka Anicin shares his early experiences in learning machine learning, highlighting the challenges and triumphs he faced. He initially struggled with advanced courses but found a more suitable introduction through Udemy, which significantly boosted his understanding of Python and machine learning concepts 1. Luka's dedication to mastering these subjects is evident in his ambitious project of manually deriving a recurrent neural network on paper, an exercise that, while grueling, deepened his comprehension 1.
I spent two months literally writing out the math of how, not just how the information flows through a recurrent neural network, but actually how you do the model weight updates as well.
---
His journey into machine learning began with a fascination for AI, spurred by a professor's work in computer vision, leading him to explore the field further and eventually become an instructor with over half a million students 2.
Career Milestones
Significant milestones in Luka's career include his transition from student to intern, where he faced numerous technical challenges but persevered through innovative solutions like cooling his laptop in a refrigerator to train neural networks 3. This hands-on experience paved the way for his first internship and subsequent professional roles, including his work at Blue Life AI and Datablooz 3.
I put my laptop in a refrigerator just to train the neural network because it was too hot.
---
Luka emphasizes the importance of building meaningful projects, not just for learning but also for showcasing skills to potential employers. He designed his courses to help students create substantial projects that stand out in job applications, moving beyond simple Kaggle projects to more complex, real-world applications 4.
Related Episodes


831: PyTorch Lightning, Lit-Serve and Lightning Studios — with Dr. Luca Antiga
Answers 383 questions

669: Streaming, reactive, real-time machine learning — with Adrian Kosowski
Answers 383 questions

671: Cloud Machine Learning — with Kirill Eremenko and Hadelin de Ponteves
Answers 383 questions

695: NLP with Transformers — with Hugging Face's Lewis Tunstall
Answers 383 questions

649: Introduction to Machine Learning — with Kirill Eremenko and Hadelin de Ponteves
Answers 383 questions

786: The Six Keys to Data Scientists' Success — with Kirill Eremenko
Answers 383 questions

SDS 473: Machine Learning at NVIDIA — with Anima Anandkumar
Answers 383 questions

661: Designing Machine Learning Systems — with Chip Huyen
Answers 383 questions

765: NumPy, SciPy and the Economics of Open-Source — with Dr. Travis Oliphant
Answers 383 questions

657: How to Learn Data Engineering — with Andreas Kretz (@andreaskayy)
Answers 383 questions
780: How to Become a Data Scientist — with Dr. Adam Ross Nelson
Answers 383 questions

826: In Case You Missed It in September 2024 — with Jon Krohn (@JonKrohnLearns)
Answers 383 questions

631: Data Analytics Career Orientation — with @LukeBarousse
Answers 383 questions
SDS 554: @JonKrohnLearns's Deep Learning Courses
Answers 383 questions













