Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore practical strategies for optimizing AI model efficiency in this 18-minute conference talk from the AI Engineer World's Fair. Learn to identify key sources of inefficiency in AI models and discover actionable techniques to improve latency and resource consumption for large-scale deployment. Examine the challenges posed by resource-demanding models and the growing on-device AI movement that imposes physical constraints on model deployment. Dive into practical solutions including model architecture selection, quantization techniques, and prompt optimization strategies. Gain insights from Dr. Shelby Heinecke, who leads an AI research team at Salesforce developing cutting-edge AI for products and academic research, with expertise spanning AI agents, LLMs, on-device AI, entity resolution, and recommendation systems.
