[agi] 3D Deep Learning, and Geometric Deep Learning

2019-04-30 Thread aneeshaa45
I'm currently a master's student currently.  While searching for a topic to research in for my master's thesis, I read a little bit about 3D Deep Learning, and Geometric Deep Learning. I'm unclear about the difference between the two. Also, about which one of them is used for tracking in Virtua

Re: [agi] Mens Latina -- 2019-04-28

2019-04-30 Thread A.T. Murray
On Tue, Apr 30, 2019 at 7:15 AM Stefan Reich via AGI wrote: > I made a joke about a chat bot speaking Latin in a video I made yesterday. > Hadn't read that mail before. Synchronicity must be real! > Modus Operandi I. Getting started. To start the artificial intelligence (AI) running, just clic

Re: [agi] My AGI 2019 paper draft

2019-04-30 Thread Matt Mahoney
Any design must start with a set of requirements. Otherwise it is directionless and doomed to fail. Examples of requirements for AGI. - Write descriptions of videos. - Pass the SAT exams. - Drive a car. - Compose and play good music. - Win at Jeopardy! Pick something. Then describe how you will s

[agi] Ramping it up

2019-04-30 Thread Stefan Reich via AGI
I'll try to 1. do daily videos 2. make paid bots constantly, so I can 3. keep the money flowing (my office contract expires in 10 days or so - HOW WILL IT CONTINUE?) 4. Approach AI Today's hypothesis: One second is a good response time to any user action. Daily video. https://www.youtube.com/wat

Re: [agi] My AGI 2019 paper draft

2019-04-30 Thread Mike Archbold
To be fair, I think YKY put perspiration into mathematical structure and it looks like a decent attempt at a fusion of logic and neural networks. But it seems like the next step could be an embryonic program. Personally I feel like I spent too long on my overall design, and some things become clear

Re: [agi] My AGI 2019 paper draft

2019-04-30 Thread Matt Mahoney
The revised paper is a bit better but really doesn't address my main concerns. I mean the 1% inspiration is done (Edison) and just the 99% persperation is left to do. Yeah, actually doing experiments and writing up the results is hard work, but that's how papers get published. Nobody cares about un

Re: [agi] Mens Latina -- 2019-04-28

2019-04-30 Thread Stefan Reich via AGI
I made a joke about a chat bot speaking Latin in a video I made yesterday. Hadn't read that mail before. Synchronicity must be real! On Mon, 29 Apr 2019 at 22:34, Costi Dumitrescu wrote: > Well... your extreme ursus appears to be deaf and only blubbers "EGO SUM > PERSONA" upon entering stuff.../

RE: [agi] My AGI 2019 paper draft

2019-04-30 Thread John Rose
Matt > "The paper looks like a collection of random ideas with no coherent structure or goal" Argh... I love this style of paper whenever YKY publishes something my eyes are on it. So few (if any) are written this way, it's a terse jazz fusion improv of mecho-logical-mathematical thought