#12 – Ali El-Sharif on Explainable Artificial Intelligence
In AI Simplified Episode 12, Ali El-Sharif and Amjad Hussain discuss Explainable AI.
Skip, recap, or review with timestamps:
0:00 Introduction
3:56 Explainable AI
5:11 AI’s Promise
5:50 Is this a Tree?
7:23 X-ray images & when AI fails to meet its promise
10:08 Supervised learning needs more attention
11:36 High quality training data sets = costly
12:28 Cross-industry data trusts
13:09 Constructing training data sets
14:46 Data trusts in research community
16:30 Throwing computing power towards data sets
17:31 Fooling ML algorithms
18:13 ML algorithms vulnerable to attacks
19:19 Bias in ML algorithms
20:14 Amazon AI Recruiting Tool
21:08 Explainability is the law
22:11 What is Explainable AI?
23:02 Explainable AI definition by DARPA
23:25 Explainable AI Target Audience
24:31 ML Explanations Benefits
24:48 Explainability leads to adoption
25:41 David Deutsch – traits of good explanations
28:12 General relativity vs. quantum mechanics
29:53 The law & corporate responsibility
32:10 Biggest black box is the human brain
32:30 Explanation is a model of the truth
33:00 Why is explainability so difficult?
33:54 Decision Trees
34:27 Interpretable model explanations don’t scale
34:55 Use Interpretable Models – If You Can
35:34 People fall in love with complex solutions
37:57 Complexity is sometimes inevitable; GPT-3 NLP Model
38:33 Why is interpretability difficult?
39:36 White box vs. black box models
41:05 Local explanation & single predictions
43:59 Post-Hoc Explanations
44:43 Explainability Options
45:19 Local Interpretable Model-Agnostic Explanations (LIME)
48:47 Explaining a prediction with LIME
49:57 LIME – Image Classifier Explanation
50:39 LIME – Text Classifier Explanation
51:16 Pros & Cons of LIME method
53:25 Overall thoughts on LIME
53:41 Foundation for Best Practices in ML
54:46 Attraction to Explainable AI research & road ahead
59:50 AI models that have conversations with humans
1:00:50 Label requirements for explainability models
1:04:00 Need for high quality data sets & collaborative models
1:07:25 Canada’s leadership in AI
1:09:40 Diversity in Canada
1:11:15 Advice for AI practitioners
1:13:30 Closing Thoughts
Why a podcast about human-centered AI?
People are either talking about artificial intelligence (AI), machine learning, deep learning, etc. in a very technical way or not at all. Having studied Computer Science and Advanced Analytics and created an AI – advanced analytics supply chain company, I understand first-hand how valuable the field is, but not everyone does. I want to change that. We can all learn principles of AI and implement them in very practical ways. Whether you want to automate a part of your business or create a new business altogether, AI can help you. My goal through this podcast is to simplify AI.
Calling it a podcast gives you a broad understanding of how we’ll communicate, but the format will be much more engaging than just audio. However, you can listen to AI Simplified like a traditional podcast too.
Amjad Hussain
Founder + Chief Executive Officer, Algo
About the host

Amjad Hussain
Amjad Hussain is an entrepreneur at heart. He founded Algo where he is the CEO during the day and AI lego blocks designer at night. He has built an intrinsically motivated global team of deep business domain experts, AI architects, computer scientists and software engineers. Algo is an always on full stack platform with deep learning, augmented reality and workflow automation woven at its core. The platform has a conversational virtual business analyst persona as its primary user interface. The company is enjoying sustainable growth creating tremendous net new value for its customers world-wide.
Amjad completed his Bachelors in Electrical Engineering with Honors from UET Lahore. He earned his Master’s degree in Electrical Engineering & Computer Science from UMIST, in the United Kingdom and an Advanced Analytics MBA from MIT. He has completed general management programs at Harvard and Stanford business schools. Amjad deeply cares about ethical issues surrounding AI and its societal impact.