Banks look to Explainable AI to address urgent governance demands
Prema Varadhan, Chief Product Architect and Head of AI at Temenos, tells FinextraTV about the recently launched Economist Unit report on AI and the thinking behind the research. We hear how AI Innovation is a differentiator in banking and how this has been impacted during Covid-19, how can it help banks support their customers and what we can expect to see from Temenos in the Explainable AI space.
eXplainable Artificial Intelligence Part I: When Does Your Organization Need to Think About XAI?
Datatonic’s Senior Data Scientist, June He, walks through when your organization needs to think about XAI, the “why” and “how”, and defining the purpose of XAI for your business.
Explainable AI explained! | #4 SHAP
▬▬ Resources ▬▬▬▬▬▬▬▬▬▬▬▬
Interpretable ML Book: https://christophm.github.io/interpretable-ml-book/
Github Project: https://github.com/deepfindr/xai-series
Paper: https://arxiv.org/abs/1705.07874
▬▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬
00:00 Introduction / Example
03:09 The paper
03:50 Calculation of Shapley values
09:34 Code examples
14:30 Plots / Visualizations
▬▬ Support me if you like ��
►Link to this channel: https://bit.ly/3zEqL1W
►Support me on Patreon: https://bit.ly/2Wed242
►Buy me a coffee on Ko-Fi: https://bit.ly/3kJYEdl
Introduction to Explainable AI (ML Tech Talks)
This talk introduces the field of Explainable AI, outlines a taxonomy of ML interpretability methods, walks through an implementation deepdive of Integrated Gradients, and concludes with discussion on picking attribution baselines and future research directions.
Chapters:
00:00 – Intro
2:31 – What is Explainable AI?
8:40 – Interpretable ML methods
14:52 – Deepdive: Integrated Gradients (IG)
39:13 – Picking baselines and future research directions
Resources:
Integrated gradients → https://goo.gle/2PxfRtq
Vertex AI → https://goo.gle/3ifu7S5
What-if-tool → https://goo.gle/3ehZWbZ
Catch more ML Tech Talks → http://goo.gle/ml-tech-talks
Subscribe to TensorFlow → https://goo.gle/TensorFlow
product: TensorFlow – General; re_ty: Publish;
Kortical – Explainable AI is possible
Kortical can audit any AI/Machine Learning model to get insights that drive confidence in AI, help remove bias in AI models and garner actionable insights to drive businesses forward