Epstein Secrets

d learning algorithm, trained on a mass of data, =an solve it with 97% accuracy. I don't think that Bob =erwick knew Deep Speech yet, a system that Andrew Ng built for Baidu =arlier this year. It does not do any Fourier transform on auditory =ata, but only raw convolutional networks. It works on phone aud

m: Joscha Bach Sent: Monday, September 7, 2015 6:36 AM To: Ben Goertzel; Jeffrey Epstein Subject: Re: Attachments: signature.asc I agree w/ Joscha's caution about discrimination tasks: They =an be often be solved rather well, but in devious ways, =y statistical supervised learning =lgorithms.

es deep =anguage models without necessarily requiring deep understanding. I am =ure that the linguists have much better ideas than me, of =ourse. — Joscha 2 EFTA_R1_02073452 EFTA02702095

From: Joscha Bach Sent: Monday, September 7, 2015 6:36 AM To: Ben Goertzel; Jeffrey Epstein Subject: Re: Attachments: signature.asc I agree w/ Joscha's cautio

d learning algorithm, trained on a mass of data, =an solve it with 97% accuracy. I don't think that Bob =erwick knew Deep Speech yet, a system that Andrew Ng built for Baidu =arlier this year. It does not do any Fourier transform on auditory =ata, but only raw convolutional networks. It works on phone aud

Joscha Bach ‹ > Sent: Monday, September 7, 2015 6:36 AM To: Ben Goertzel; Jeffrey Epstein Subject: Re: Attachments: signature.asc I agree w/ Joscha's caution about discrimination tasks: They =an be often be solved rather well, but in devious ways, =y statistical supervised learning =lgorithms.

From: Joscha Bach ‹ > Sent: Monday, September 7, 2015 6:36 AM To: Ben Goertzel; Jeffrey Epstein Subject: Re: Attachments: signature.asc I agree w/ Joscha's ca

es deep =anguage models without necessarily requiring deep understanding. I am =ure that the linguists have much better ideas than me, of =ourse. — Joscha 2 EFTA_R1_01610677 EFTA02489921

nd has co-invented a bunch of important neural network types. (Other Great Old Men are Jeff Dean, from MIT, currently leading an AI team at Google, Andrew Ng, who went from Stanford to Baidu, Peter Norvig: Google, and Stuart Russel.) Generally, the current generation of Al folks do not tend to big univers

m> Date: Friday, December 25, 2015 Subject: Interesting people, funds etc To: Jeffrey Epstein <[email protected]> Forwarded message From: Joscha Bach <1 Date: Friday, 25 December 2015 Subject: Interesting people, funds etc To: Jeffrey Epstein <[email protected]> Dear Jeffrey, I hope this fi

ntly depleted again, could you please help me out again? (Still embarrassed to ask.) With best wishes for what mortals consider to be the holidays, Joscha please note The information contained in this communication is confidential, may be attorney-client privileged, may constitute inside information

nd has co-invented a bunch of important neural network types. (Other Great Old Men are Jeff Dean, from MIT, currently leading an AI team at Google, Andrew Ng, who went from Stanford to Baidu, Peter Norvig: Google, and Stuart Russel.) Generally, the current generation of Al folks do not tend to big univers

ey Epstein <[email protected]> Subject: Fwd: Interesting people, funds etc Date: Fri, 25 Dec 2015 19:22:58 +0000 Forwarded message From: Joscha Bach <1 Date: Friday, 25 December 2015 Subject: Interesting people, funds etc To: Jeffrey Epstein <[email protected]> Dear Jeffrey, I hope this fi

gain, could you please help me out again? (Still embarrassed to ask.) EFTA00838033 With best wishes for what mortals consider to be the holidays, Joscha please note The information contained in this communication is confidential, may be attorney-client privileged, may constitute inside information

esentation problem in cognitive model with limited power. However, I might be wrong at least in the case of low level sensory processing. Last year, Andrew Ng and a bunch of Googlers extracted object categories from 30 million random Youtube frames, using an unsupervised EFTA00700864 neural network. Mer

From: Joscha Bach To: "S.M. Kosslyn" <=MI > Cc: Jeffrey Epstein <a Subject: Re: Today's discussion Date: Tue, 19 Feb 2013 03:16:16 +0000 Dear Stephen, Berlinale

as gotten quite long again; sorry for that. I find that it very helpful to have an opportunity to spell these arguments out! Thank you, and cheers! Joscha EFTA00700865