Cheaper, Faster Machine Learning: Quantization and Distillation

​Quantization and distillation are essential techniques for optimizing machine learning and AI models. Both techniques aim to make models smaller in memory, computationally faster, and also cheaper whilst having minimal performance tradeoffs. We'll explore both the theory behind these techniques and practical applications as well. Whether your an AI practitioner, enthusiast, or professional, we welcome everyone to join us for this session.