Breaking Into AI for Science - Alishba Imran of UC Berkeley BAIR, Arc Institute, CZ Biohub, Voltx

<p>Alishba Imran is a deep learning researcher at UC Berkeley's BAIR AI Lab, a Research Fellow at the Arc Institute, a former Research Intern at the Chan Zuckerberg Biohub, co-founder of battery tech startup Voltx, and co-author of "AI for Robotics: Toward Embodied and General Intelligence in the Physical World"</p><p>See below for episode links, chapters, and our socials. Hosted by Nabil Laoudji.</p><p>Support the podcast! Subscribe to our newsletter: <a href="https://www.discoveryengines.co/" target="_blank">www.discoveryengines.co</a>. Thanks for watching 🙏🤙</p><p><strong>Episode Links:</strong></p> <ul> <li><a href="https://www.linkedin.com/in/alishba-imran-/" target="_blank">Alishba's LinkedIn</a></li> <li><a href="https://x.com/alishbaimran_/" target="_blank">Alishba's Twitter</a></li> <li><a href="https://link.springer.com/book/10.1007/979-8-8688-0989-7" target="_blank">"AI for Robotics" book</a></li> <li><a href="https://arcinstitute.org/" target="_blank">Arc Institute</a></li> <li><a href="https://bair.berkeley.edu/" target="_blank">UC Berkeley BAIR AI Lab</a></li> <li><a href="https://www.czbiohub.org/" target="_blank">Chan Zuckerberg Biohub</a></li> <li><a href="https://arxiv.org/html/2410.11281v1" target="_blank">DynaCLR Paper</a></li> <li><a href="https://biopunklab.com/" target="_blank">Biopunk Lab</a></li> </ul><p><strong>Chapters:</strong></p><ul> <li>(00:00) - Preview & Introduction</li> <li>(05:02) - Why AI for Science?</li> <li>(10:34) - Bootstrapping Your Own Learning</li> <li>(16:02) - Why Battery Testing Matters: Launching Voltx</li> <li>(20:19) - Batteries, Raw Earth Minerals: Incremental vs Transformative Chemistries</li> <li>(23:54) - The Business Side of Deep Tech Entrepreneurship</li> <li>(29:14) - The State of Battery Tech Today</li> <li>(30:50) - Working with Chan Zuckerberg Biohub</li> <li>(33:37) - DynaCLR For Contrastive Learning of Cell State Dynamics</li> <li>(36:21) - Why Self-Supervised + Contrastive Learning</li> <li>(41:06) - Generalizing to Different Cells Contexts With Embeddings</li> <li>(42:06) - Microscopy or ML Advancements for Unlocking Progress</li> <li>(43:54) - Managing Terabytes of Data</li> <li>(46:51) - Arc Institute: Collecting Largest Single Cell Dataset</li> <li>(48:40) - Role of Tech-Founder Funded Institute To Advance Foundational Work</li> <li>(50:41) - Book Launch! Merging Classical Robotics Methods With Cutting-Edge Deep Learning</li> <li>(53:42) - Robotics Progress: Hype vs Reality</li> <li>(57: