Why We Need A Global Artificial Intelligence Platform to Prevent Misinformation
Artificial intelligence (AI)is crucial to combat the spread of misinformation and propaganda on the internet.
AI is able to analyze and quantify an enormous amounts of information generated daily on a scale that’s impossible for humans, ultimately, it’s up to us to be part of the process of fact-checking to inform people worldwide.
In 2021, the risk of a global pandemic suddenly became a new reality for all and everybody.
We are systematically fed by biased, mis- and dis- information. The big tech digital platforms such as Google, Facebook, Baidu or Tencent should do more to tackle fake news and cyber propaganda.
Global AI Platform (GAIP) is designed to monitor the world’s states of affairs in real time making predictions about future events based on the world’s causal model enriched with real world’s statistics by analysis of world news, megatrends and global threats and risks.
It is also to apply global trends analysis, with reversal megatrends/risks included, to predict future world events, as trends that have a causal effect on a global scale.
Global AI Platform features causal machine learning algorithms, as deep causal neural networks of various architectures, to forecast all the possible future scenarios, where nodes and edges represent causal factors/variables/events/ and causal relationships/processes/mechanisms/paths/functions, respectively.
A reversible nonlinear cyclical causal model could be defined as the joint distribution P(O, P, X) over a set of Causal DNN outputs O, inputs P, and intermediate causal variables X, where controlled megatrends are weighted inputs, intermediate variables are the set of all processing units/neurons/functions/megatrends, and the causal effects as possible future world events are output predictions with feedback causal influences. It is modelled as a complete deep forward and backward neural network with all possible causal path topologies.
Combining the reasoning power of symbolic AI systems with the pattern recognition power of ML neural networks, the Real/Causal AI system should be able to identify causal variables and separate their effects on the environment.
Note that the majority of current successes of ML reduce to large scale pattern recognition on suitably collected independent and identically distributed (i.i.d.) data. It supposes that random observations in a problem space are independent of each other and have a constant probability of occurring. The assumption is that, with many examples, the ML model will be trained or schooled to encode the general distribution of the problem into its parameters, while in the real world, distributions often change due to the dynamic characters of environments that cannot be considered and controlled in the fixed training data.
“Generalizing well outside the i.i.d. setting requires learning not mere statistical associations between variables, but an underlying causal model.” So, develop a causal machine learning model that can predict outcomes based on real regularities instead of statistical regularities. It is not surprising that during the coronavirus pandemic, machine learning systems began to fail as trained on statistical regularities instead of causal relations.
