ynonym00s
Micheal Jordan (Berkeley), Perspectives and Challenges in ML
Do Our Questions Create the World?
Ask HN: What are some approaches to combining symbolic AI with deep learning?
I'm starting a Masters in CS soon and I'd like to explore ideas that combine old school AI (for e.g. symbolic reasoning) with the modern probabilistic approaches (neural networks).Would anyone in the field be kind enough to provide a brief overview of what is happening at this intersection with paper suggestions for further reading?
Re:Einstein's travel diaries reveal attitudes towards people he met in...
on Wednesday June 13, 2018 @09:54AM (#17303037)
I am not sure why this has been downvoted. Will somebody care to explain?
Re:How Many Genes Do Cells Need? Maybe Almost All of Them
on Monday April 23, 2018 @03:51PM (#16906787)
Would you mind explaining what you mean by 'commented sections' in DNA? I have a very basic understanding of DNA.
Re:In Praise of ADHD
on Saturday March 17, 2018 @05:00PM (#16609036)
Hello, I'm interested in your taskmanager app. Is your email [redacted]?
The era of the cloud’s total dominance is drawing to a close
Re:A.I. And Big Data Could Power a New War on Poverty?
on Tuesday January 02, 2018 @02:04PM (#16054404)
hmm, it is a war on poverty, not on the poor.
Re:Adderall Risks: Much More Than You Wanted to Know
on Saturday December 30, 2017 @10:19AM (#16035579)
A friend of mine who has ADHD takes Vyvanse instead. Does it have similar risks?
Re:Big Tech Is Going After Health Care
on Wednesday December 27, 2017 @04:47PM (#16018319)
Would love to get some insight into the work at Verily or DeepMind Health for a software developer interested in working in healthcare.
Re:Walter Pitts pioneered neural networks. Then he lit his entire PhD ...
on Friday December 22, 2017 @03:49PM (#15990768)
So, w.r.t to Pitt's research, proving that the brain could compute anything (like a Turing machine) does not help in understanding how it does one particular thing, for e.g. language?
Re:Walter Pitts pioneered neural networks. Then he lit his entire PhD ...
on Friday December 22, 2017 @03:39PM (#15990712)
"There was a catch, though: This symbolic abstraction made the world transparent but the brain opaque. Once everything had been reduced to information governed by logic, the actual mechanics ceased to matter—the tradeoff for universal computation was ontology. ... anything and everything … can be done by an appropriate mechanism, and specifically by a neural mechanism—and that even one, definite mechanism can be ‘universal.’ Inverting the argument: Nothing that we may know or learn about the functioning of the organism can give, without ‘microscopic,’ cytological work any clues regarding the further details of the neural mechanism.”
- Would anyone mind to ELI5 this for me?
Ask HN: What are some interesting applications of ML in biomedical imaging?
I want to apply ML to do neuroscience research. I may get a chance to do that in a brain imaging lab next year. Are there any particularly exciting research areas under the neuroimaging/ML umbrella?