From Explainable AI via Causal AI to Real AI: XAI > CAI > RAI
The number of Explainable AI (XAI), or Interpretable AI, or Explainable Machine Learning (XML) research articles that discuss the development, implementation, or practice of explanations/interpretations in today's AI/ML/DL systems have been constantly increasing, now exceeding 10 000 research papers (Trends in Explainable AI (XAI) Literature).?
Its expansion growth covers different fields of study and fragmented as: XAI-Computer Science and XAI-Mathematics, XAI-Physics, XAI-Medicine, XAI-Psychology, XAI-Biology, XAI-Engineering, XAI-Economics, XAI-Law, XAI-Business and XAI-Philosophy.
Real XAI is integrating most specific XAI models by its Reality Model Enginery (RME), governing its effective interactions with the world, while operating machine data understanding, learning and inference, self-knowledge, predictions and explanations, actions and reactions.
It underlies all the meaningful representations, modeling or simulation of the world, its realities and features, be it causal models, mathematical models, scientific models, mental models (mental representations, mental simulation, schema), conceptual models, AI models or ML algorithms.
Real XAI Development Algorithm: RME Enginery: Symbolic AI > Statistical Learning > Machine Learning > Deep Learning > Explainable ML/AI > Causal ML > Causal AI > Real AI = Trans-AI > Man-Machine Hyperintelligence = Singularity AI
AI, Explainable AI, or Interpretable AI, or Explainable Machine Learning
Today's AI is loosely interpreted in terms of human intelligence, perception, cognition, reasoning or behavior. It is usually a set of different technologies, including any type of software or hardware components, that supports human-like machine intelligence and learning, as expert systems, computer vision, natural language understanding, natural language generation, natural language processing, speech recognition, automation, robotics, etc.
AI is commonly defined after human intelligence as the ability to perceive, to pursue goals, to initiate actions and to learn from a feedback loop. It is like a definition of AI by the High-Level Expert Group on Artificial Intelligence (AI HLEG) of the European Commission (EC):
“Systems that display intelligent behaviour by analysing their environment and taking actions – with some degree of autonomy – to achieve specific goals.”
Then a classic thermostat is AI. This device is also able to perceive (measure the temperature of the room), pursue goals (the programmed temperature), initiate actions (regulate the thermostat) and learn from a feedback loop (stop once the programmed temperature has been reached).
Now, Explainable AI (XAI), or Interpretable AI, or Explainable Machine Learning (XML), is defined as "AI in which humans can understand the decisions or predictions made by the AI".
Or, "Explainable AI is "a set of tools and frameworks to help you understand and interpret predictions made by your machine learning models".
As to DARPA, the Explainable AI (XAI) program aims to create a suite of machine learning techniques that:
The number of XAI research articles that discuss the development, implementation, or practice of explanations/interpretations in modern AI/ML/DL systems, as registered on the Semantic Scholar database, have been increasing exponentially, now exceeding 10 000 research papers (Trends in Explainable AI (XAI) Literature).?
Its expansion growth covers different fields of study: XAI-Computer Science and XAI-Mathematics, XAI-Physics, XAI-Medicine, XAI-Psychology, XAI-Biology, XAI-Engineering, XAI-Economics, XAI-Law, XAI-Business and XAI-Philosophy. Some examples from the XAI-CS are as follows:
The keywords include: "explanation", “explainability”, “interpretability”, “explainable ai”, “explainable artificial intelligence”, “interpretable ml”, “interpretable machine learning”, “interpretable model”, “feature attribution”, “feature importance”, “global explanation”, “local explanation”, “local interpretation”, “global interpretation”, “model explanation”, “model interpretation”, “saliency”, “counterfactual explanation”.
In all, there is no single clear definition of XAI, marked with free or extravagant interpretations, which, instead of explaining or clarifying causes, contexts and effects or consequences, is confusing, confounding or misunderstanding things to be explicated, defined, or interpreted, elucidated or explicated.
There are many different things, events, objects, and facts which require explanation, as there are many different things that can be used to explain them. Types of explanation are as various as the number of things to be explained: Scientific, Deductive-nomological, Statistical, Functional, Historical, Psychological, Reductive, Teleological, Methodological explanations.
Causal explanations are historically viewed as to be of universal kinds of explanation comprising all ways of explaining something. They serve as the basic frame which makes the world and its realities and features easier to understand, define, quantify, visualize, or simulate by referencing it to causal world knowledge, its laws and rules, patterns and theories.
AI is emerging as a new intelligent entity, novel type of intelligence, machine intelligence or "alien intelligence", only inspired by and CREATED by human intelligence, as the brainchild or "mind children".
Real AI is an intelligent system generating its causal models, algorithms and computer programs as well.
Daniel Dennett had wisely suggested that we should not model AI on humans at all. These are not artificial people, but a completely new type of entity – one he compares with oracles: entities that make predictions, but unlike humans have no personality, conscience or emotions.
The Principles of Real AI, Causal ML and Intelligent Machines
Principle 1: Science and Technology and Human Practice are all about discovering and applying causal relationships, their processes, mechanisms and effects
Principle 2: Intelligence consists in simulating and modeling, understanding and effective interacting with the world and reality, its causality and causation, variables and interactions, causative patterns, rules and laws of reality
Principle 3: Artificial Intelligence consists in Causal Machine Intelligence and Learning
Principle 4: Machine Intelligence postulates Causal Intelligence
Principle 5: Machine Learning postulates Causal Learning
领英推荐
Principle 6: No Causal Intelligence, no Machine Intelligence
Principle 7: No Causal Learning, no Machine Learning
Principle 8: Non-Causal Machine Intelligence and Learning are Non-Intelligent AI
Principle 9: Non-Causal Machine Learning is not Real Machine Learning
Principle 10: Real/Causal AI embraces all the ethical principles for responsible and trustworthy AI (as?OECD AI Principles)
The biggest trend in AI and ML and DL
The biggest trend in AI and ML is building Causal Machine Intelligence and Learning. The idea is to integrate causality, learning causal patterns, correlations and associations, rules and laws and effects from data.
Machine learning based on statistics and probabilities, correlational pattern recognition, like LMMs, as ChatGPT or LaMDA, is insufficient for meaningful predictions and reliable decision-making.
New approaches to machine intelligence and learning (MIL) based on principles of causal reasoning, modeling and analysis provide a promising path forward to Real/True/Generalized AI.?
The idea of?causal/physical/real AI?was first generated as part the Encyclopedic AI project (A. Sh. Abdullaev, Preprint Knowledge Base of Encyclopedic Artificial Intelligence, Moscow, 1989, Academy of Sciences of the USSR).
The key assumption is “Machines' lack of understanding of causal relations is perhaps the biggest roadblock to giving them human-level intelligence.” [The Book of Why: The New Science of Cause and Effect, 2018]
In reality, it is humans' lack of understanding of causal relationships as interactions or productive correlations and associations is the biggest roadblock to giving machines human-level intelligence.
Causal AI/ML and Correlational AI/ML: Causation postulates Correlation, and Correlation implies Causation
Correlation?means there is a statistical association between variables.?Causation?means a real association between variables when a change in one variable causes a change in another variable, and VICE VERSA.
Correlation and causation are two entangled things at all levels, from the quantum level to the cosmological level of the whole universe: “correlation implies causation”, while "causation postulates correlation".
First of all, there is one real relationships in the world and reality, which is causation or cause and effect, all the the rest, as resemblance, contiguity, or wholeness, have the less reality, if any.
Any mature science and?good researchers in any domains?are implicitly guided by the ten fundamental features of real causation:
"The cause precedes the effect (time order). The cause co-occurs with the unaffected entity in space and time (co-occurrence). Causes and their effects are the result of a web of causation (preceding causation). The intensity, frequency, and duration of the cause are adequate and the susceptible entity can exhibit the type and magnitude of the effect (sufficiency). The cause effectively interacts with the entity in a way that induces the effect (interaction). And, the entity is changed by the interactions with the cause (alteration)".
Besides, causality has all the major attributes of relationship: symmetry, transitivity and reflexivity.?
Still, many dogmatically presume that "correlation doesn't imply causation" and that causality is the asymmetrical relations of cause and effect, the cause (independent variable) must precede the effect (dependent variable) in time, as?the treatment/intervention 'causes' the outcome in the RCTs (A/B) experiments.
Causation is defectively defined as?the relationships between independent, control, and dependent variables, as?a linear, asymmetrical relationship between two variables X and Y such that changes in X lead to changes in Y, and the key difference between association and causation lies in the confounding.
The causal metamodel is confused as a three-level abstraction, the ladder of causation, as
associations/probabilities/correlations/regularities/patterns (seeing/observing);
causality/intervention (doing);
counterfactuals/but-for causation/sine qua non?causation/physical laws (thought experiment/imagination/reasoning). [ Pearl, J.?Causality: Models, Reasoning, and Inference. Vol. 64 (Cambridge University Press, 2000)].
This all corrupts the whole science and engineering of causality and causation, the real nature of causal processes and mechanisms, causal analysis (regularity, probabilistic, counterfactual, and manipulative), reasoning and inferences and models, impact, efficacy and effectiveness, measures and effects.
The linearity of causality brings to the poor conception of causal graph or causal network (also known as path diagrams,?causal Bayesian networks) as a topologically ordered directed acyclic graph, DAG, with no directed cycles, where one event (X) is to cause another if it raises the probability of the other (Y).
In statistics, econometrics, epidemiology, genetics and related disciplines, causal graphs as DAGs are?probabilistic graphical models encoding assumptions about the data-generating process. Such?statistics revolves around the analysis of relationships/associations/correlations among multiple variables.
In reality, causal structure or causal system is the network graph of causal interrelationships [associations/correlations/interactions] among or between a set of causal variables, and causal discovery algorithms are the problem of learning the causal structure, patterns and correlations, rules and laws, from data, observational and experimental, simulation or theoretical, real-world or synthetic, structured or unstructured, digital or analogue.?Real machine statistics revolves around the analysis of causal relationships among multiple variables/nominal, ordinal, interval, ratio, numeral data.