I will be talking about HTM systems at AI With the Best online conference. My talk and abstract are below:
Hierarchical Temporal Memory: Computing Like the Brain
Most of today’s AI technologies are extensions of ANN models that were envisioned twenty years ago. While they have some amazing capabilities, they are not truly intelligent. To attain truly intelligent machines, our approach is to understand the only thing we can all agree is intelligent today: the human brain. HTM is an AI technology that is biologically-constrained. All major algorithms at work in an HTM system were uncovered by years of intensive neuroscience research. In this presentation, I’ll describe the major mechanism of HTM at a high level, and lay a path towards the future of truly intelligent machines.
I just got all set up to do this online conference, and it is run very smoothly. Seems like this is going to be a good event, so if you are interested in learning a bunch about the AI landscape for cheap ($60USD), I suggest signing up for this event. Even if you miss the speakers, they are all being recorded and you can watch them later.
You also have the chance for live Q&A and 1-on-1 sessions with some of the conference speakers. See the agenda here. Peter Norvig (Google) and Ian Goodfellow (OpenAI) are also speakers.
I’ve been vacilating about this, but having the videos recorded for later viewing sounds like a good time. Plus $60 for some fun education is worth it! Matt can you PM me the discount code as well, please.
It was really good. The technical explanations were very effective.
In my opinion, the only thing missing were some initial use cases examples to show the power of the technology and to put things in perspective and perhaps a 1000 ft view how the SDR, and the poolers fit together.
Maybe they were there and I missed it since I was a minute or so late due to another talk going over time.
Your talk was particularly good, Matt. You had a lot more content than most of the speakers, and you also had both your video and audio working, which wasn’t the case for some other talks.
I thought the talk was especially good, containing both a high level
overview and more detail about how the system works. The animations were
especially useful for visualizing how the SDR inference/learning works.
