Dexa/This Week in ML & AI

Published Oct 14, 2024

ML Models for Safety-Critical Systems with Lucas García - 705

Lucas García delves into the integration of ML models in safety-critical systems, highlighting transformers' role in model verification and industry applications like aviation, and unveiling the W-model's structure for robust verification and validation amid hardware constraints. Discover the intricacies of neuron coverage methodologies and the potential of convex neural networks for achieving higher certification standards.

Episode Highlights

Topics covered

Questions from this episode

- How can artificial intelligence (AI) be regulated?
  Asked by 71 people
- How can we integrate AI into our business processes?
  Asked by 55 people
- What's next in large language models (LLMs)?
  Asked by 33 people
- Should artificial intelligence be regulated?
  Asked by 23 people
- What techniques are used with large language models (LLMs)?
  Asked by 23 people
- How do you leverage different models in machine learning?
  Asked by 20 people
- What are the challenges of deploying AI?
  Asked by 13 people
- What are the challenges in machine learning?
  Asked by 11 people
- How can trust be built in AI systems?
  Asked by 7 people
- What is the process of training a machine learning model?
  Asked by 7 people
- What's the situation with political regulations on AI?
  Asked by 6 people
- How can AI ensure reliable results?
  Asked by 5 people
- How can trust be built into AI systems?
  Asked by 4 people
- How do we verify AI reasoning?
  Asked by 4 people
- Is life simple?
  Asked by 4 people

Episode Highlights

Related Episodes

Deploying Edge and Embedded AI Systems with Heather Gorr - 655
Answers 383 questions
Ensuring LLM Safety for Production Applications with Shreya Rajpal - 647
Answers 383 questions
AI Robustness and Safety with Dario Amodei - #75
Answers 383 questions
Mamba, Mamba-2 and Post-Transformer Architectures for Generative AI with Albert Gu - 693
Answers 383 questions
How a Global Energy Company Adopts ML & AI with Nicholas Osborn - #150
Answers 383 questions
How Microsoft Scales Testing and Safety for Generative AI with Sarah Bird - 691
Answers 383 questions
Composing Graphical Models With Neural Networks, w/ David Duvenaud - #96
Answers 383 questions
AI Sentience, Agency and Catastrophic Risk with Yoshua Bengio - 654
Answers 383 questions
Delivering AI Systems in Highly Regulated Environments with Miriam Friedel - 653
Answers 383 questions
Security and Safety in AI: Adversarial Examples, Bias and Trust with Moustapha Cissé - #108
Answers 383 questions
Automated Machine Learning with Erez Barak - #323
Answers 383 questions
Deep Learning, Transformers, and the Consequences of Scale with Oriol Vinyals - #546
Answers 383 questions
ML Use Cases at Think Big Analytics with Mo Patel & Laura Frølich - #54
Answers 383 questions
The Case for Hardware-ML Model Co-design with Diana Marculescu - #391
Answers 383 questions
Energy Star Ratings for AI Models with Sasha Luccioni - 687
Answers 383 questions