Machine learning is “Competence without Comprehension” as famously noted by Dan Dennett, the pre-eminent philosopher of our times. There are two aspects to Machine Learning (ML) “comprehension”.
Artificial General Intelligence (AGI) hopes to infuse ML with comprehension. The other less lofty aspect is that WE would like to “comprehend” how ML reaches its decisions and predictions! To accomplish the latter, we need “Explainable ML” – explanation is the evidence of comprehension . . .
Causation is the most important connection in the Universe – why? The cause-effect relationship among different entities alone provides the invariant basis for the explanation of the causal chain that leads to a decision or a prediction. ML may be able to pull together information using a deep neural network from, say, various vital signs of a patient and provide a decision (“move to ICU now”) or prediction (“oxygenation level will be below threshold in 2 hours”). But when ML cannot provide the explanations, physicians cannot perform “what-if” and counterfactual thought-experiments necessary to tease out the root causes.
The conundrum in ML is that if predictions based on correlations are accurate “enough” and applies to related cases (generalizable) “most of the time” for practical use, why bother about WHY ML worked? The problem is “enough” and “most of the time”; because they are probabilistic statements, was ML’s effectiveness a “chance event” or was there an enduring basis for us to believe that it will work in other cases – in other words, what is the whole “solution space”?!
When ML is not explainable, it is hard nigh impossible to know the perimeter of the Solution Space; when we cannot surmise the extend of this space, we feel antsy! We need to comprehend the solution space coverage and reasons for it – Explanation is the evidence that we have comprehended the competence of our ML!
Explanation needs knowledge of cause-effect relationships . . .
CALLING on Data Scientists to incorporate Causality into your algorithms in your application domain! Here are my recent attempts to incorporate Causality into IoT –
(A) “Evidence-based Prescriptive Analytics, CAUSAL Digital Twin and a Learning Estimation Algorithm”, April 2021 at https://arxiv.org/abs/2104.05828
- Causality & Causal Graph; Conditions for a DAG to be a Causal Graph; Causal Discovery & Causal Estimation – Causal Graph in IoT use cases can be elicited from domain-experts
- Non-traditional Neural Network algorithm; Causal Graph integrated into NN; Full derivation in the appendix
(B) “Stochastic Formulation of Causal Digital Twin – Kalman Filter Algorithm”, May 2021 at https://arxiv.org/abs/2105.05236
- Stochastic formulation; SVAR model recast as State-space model
- Kalman Filter & Smoother algorithm to estimate causal factors
Dr. PG Madhavan