Developing a deep learning project (case study on transformer)

❤️ Become The AI Epiphany Patreon ❤️ ► https://www.patreon.com/theaiepiphany ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ In this video, I talk about how I work on my deep learning projects on the example of the transformer which I've recently open-sourced. You'll learn about: ✔️ Snippets of my personal story ✔️ How I think about approaching a new project ✔️ Problems I encountered developing the transformer ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ ✅ My transformer implementation: https://github.com/gordicaleksa/pytorch-original-transformer ✅ The Annotated Transformer blog: http://nlp.seas.harvard.edu/2018/04/03/attention.html ✅ Original paper: https://arxiv.org/abs/1706.03762 ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ ⌚️ Timetable: 0:00 Open-sourcing original transformer and why 3:00 Creating great projects takes time 5:40 My time management 9:00 My story and embracing failures 12:05 Overview of the transformer project 14:03 Data and task definition 15:57 Training loop 20:10 Problems I encountered 21:44 Beam search fun 23:10 BucketIterator fun 25:35 Optimizing things to speed up the loop 26:25 Translating from English to German and vice versa 30:00 Hardware requirements 30:47 Wrapping things up ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 💰 BECOME A PATREON OF THE AI EPIPHANY ❤️ If these videos, GitHub projects, and blogs help you, consider helping me out by supporting me on Patreon! The AI Epiphany ► https://www.patreon.com/theaiepiphany One-time donation: https://www.paypal.com/paypalme/theaiepiphany Much love! ❤️ ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 💡 The AI Epiphany is a channel dedicated to simplifying the field of AI using creative visualizations and in general, a stronger focus on geometrical and visual intuition, rather than the algebraic and numerical "intuition". ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 👋 CONNECT WITH ME ON SOCIAL LinkedIn ► https://www.linkedin.com/in/aleksagordic/ Twitter ► https://twitter.com/gordic_aleksa Instagram ► https://www.instagram.com/aiepiphany/ Facebook ► https://www.facebook.com/aiepiphany/ 👨