What is Zero-Shot Learning? VIDEO
Want to play with the technology yourself? Explore our interactive demo → https://ibm.biz/BdKkPk
Learn more about the technology → https://ibm.biz/BdKky2
Humans can on average categorize 30,000 unique object categories, but how can AI systems distinguish between different things? Zero-shot learning can be done through various methods like attribute based and embedding based learning. In this video Martin Keen explains how technologists are giving AI systems the categorization power that we take for granted.
AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/BdKkyq
Other Videos By IBM Technology 2024-09-24 Not just a chatbot: Build virtual agents that are actually helpful with gen AI 2024-09-23 What is Granite? 2024-09-23 IBM Tech Now: IBM & Salesforce, custom foundation models on watsonx.ai, and Mixture of Experts 2024-09-20 Mobile Threat Defense: Protecting Your Mobile Devices from Attacks 2024-09-20 OpenAI o1 preview, Agentforce, AI in fantasy football, and machine unlearning 2024-09-19 Apple's AI Advantage 2024-09-19 Putting AI to work for Finance 2024-09-18 Reproducibility in AI Systems 2024-09-17 Will Siri ever be good? 2024-09-17 What are DNS Zones And Records? 2024-09-16 What is Zero-Shot Learning? 2024-09-13 Apple Intelligence, Reflection 70B, open-source AI agents, and LLM research ideas 2024-09-12 Unmask The DeepFake: Defending Against Generative AI Deception 2024-09-11 What is Artificial Superintelligence (ASI)? 2024-09-10 Rewriting the future: how devs are driving gen AI 2024-09-09 RAG vs. Fine Tuning 2024-09-09 IBM Tech Now: IBM at the US Open and the new Telum II processor 2024-09-06 NEO 1X Robot, OpenAI chips, The AI Scientist, and the future of prompt engineering 2024-09-05 Preventing a Global Software Catastrophe: Disaster Recovery Strategies & Lessons Learned 2024-09-04 Primary and Secondary DNS: A Complete Guide 2024-09-04 How open source can democratize AI