Back to the Future
Also in today's edition: BI market: Only a few will survive, The Rise and Fall of Netscape: A Lesson in Web History & What did people search for in AI?
How to develop a human brain in a machine? The quandary to solve the most difficult puzzle – in this case, the brain – and to simulate in a machine is yet to be solved and implemented. Scientists are toying with numerous neural models – Feedforward artificial neural networks, Perceptron, Multilayer Perceptron neural networks, Recurrent neural networks and others – but are far from achieving a breakthrough.
Researchers are now revisiting the once-popular Good-Old-Fashioned Artificial Intelligence (GOFAI) for constructing autonomous intelligent software as intelligent as a human. Symbolic AI systems are one of the examples of GOFAI that aims to take machines to human levels of comprehension. Symbolic AI played upon the human brain’s ability to figure out the world in terms of symbolic interconnections and representations. There’s a set of rules to define the concepts that capture everyday knowledge.
Symbolic models have the ability to grasp compositional and causal knowledge, which can pave the way for the flexible generalisation of AI models. While Symbolic models focus on compositional and causal knowledge, neural networks in deep learning are able to draw directly from raw data, which means they have to be retrained over and over to learn new tasks.
Keep reading with a 7-day free trial
Subscribe to Sector 6 | The Newsletter of AIM to keep reading this post and get 7 days of free access to the full post archives.