Re:It takes a lot of energy for machines to learn
by MAXPOOL on Wednesday December 30, 2020 @04:05PM
(#25586096)
550–600 million years of hyperparameter tuning and neural architecture search using an evolutionary algorithm is nothing to laugh at.
But the actual learning process of a single brain uses very little training examples and is very energy efficient. A brain that uses only 20 watts of power.
Re:It takes a lot of energy for machines to learn
by polishdude20 on Thursday December 31, 2020 @02:29AM
(#25590439)
Yeah it's as if we evolved to have a brain that is good at learning itself. We aren't good at any one thing except learning.
Re:It takes a lot of energy for machines to learn
by ravi-delia on Wednesday December 30, 2020 @03:59PM
(#25586032)
That is a matter of great debate. Although most people's brains wind up settling on basically identical structure over time, case studies with injured or disabled people often display incredible adaptability (ie the occipital lobe in a blind person). If indeed the brain learns most of what it knows from experience, than its (comparatively) low energy consumption would come from greater efficiency. That definitely seems possible; as a basic unit of machine learning the neuron is much more specialized than the transistor, and far slower.
Re:It takes a lot of energy for machines to learn
by anaphor on Wednesday December 30, 2020 @04:19PM
(#25586248)
My interpretation of what the parent meant is that the cognitive processes which support language acquisition (which may be mostly domain-general) are already optimized for this task, for which there is a sensitive period during certain years where you need to be exposed to certain inputs, or else you never fully acquire language. See: https://en.wikipedia.org/wiki/Genie_(feral_child)
The human brain is the output of an incredible number of generations of training, representing a vast consumption of energy. Most of the learning that informs the brain happened before this hypothetical five-year-old was even born.