Epstein Secrets

Nietzsche Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC CTO, Genescient Corp Chairman, Humanity+ Adjunct Professor of Cognitive Science, Xiamen University, China Advisor, Singularity University and Singularity Institute "My humanity is a constant self-overcoming" -- Friedrich Nietzsche <?xml version="1

DeSTIN (distinct from his commercial one) to CUDA, a parallel processing language that runs on Nvidia graphics cards. This should enable us to run DeSTIN scalably for robot vision. thx ben On Fri, May 27, 2011 at 5:29 PM, Ben Goertzel <ben@goertzeLorg> wrote: > Hi Jeffrey, > Thanks so much for you

A02540873 Ben Goertzel, PhD CEO, Novamente LLC and Biomind LLC CTO, Genescient Corp Chairman, Humanity+ Adjunct Professor of Cognitive Science, Xiamen University, China Advisor, Singularity University and Singularity Institute "My humanity is a constant self-overcoming" -- Friedrich Nietzsche <?xml version="1

ow links into my OpenCog framework.... He views DeSTIN as an autonomous approach to human-level AGI, which I'm a bit skeptical of, but I want to use DeSTIN as a perceptual processing lobe within OpenCog, and I've had a student in China (actually a Dutch guy in China for a 6 month internship) working on

sentence before "==>"; and the sentence to the right side of "==>" was one of the sentences generated by NLGen. Example 1: I study mathematics at Xiamen University. ==> I study mathematics at Xiamen\_University. Example 2: The red block is next to the blue cup. ==> The red block is next\_to the blue cup. Ex

nderstanding or generation. A CogPrime approach to speech would be quite feasible to develop, for instance using neural-symbolic hybridization with DeSTIN or a similar perceptual-motor hierarchy. However, this potential aspect of CogPrime has not been pursued in detail yet, and we won't devote space to

o something to be said for physical robots that interact with all the messiness of the real world. With this in mind, in the Artificial Brain Lab at Xiamen University in 2009-2010, we con- ducted some experiments using OpenCog to control the Nao humanoid robot [GD09]. The goal of that work was to take the same code

a spatiotemporally hier- archical deep learning system is an effective way to handle representation and learning of low-level sensorimotor knowledge. DeSTIN is one example of a deep learning system of this nature that can be effective in this context. i. One effective way to handle goals is to represent