Are you an AI expert, or are you planning to be? There are three fundamental challenges that will underlie the major AI evolutions over the next decade. These are the three areas where you NEED to understand the fundamentals – before AI moves so fast that you’ll never catch up. Let them guide your deep study for the year ahead. Check them out in this new YouTube post: Live free or die, my friend – AJ Maren Live free or…
If you are branding yourself as an AI/neural networks/deep learning person, how well do you really know the backpropagation derivation? That is, could you work through that derivation, on your own, without having to find a tutorial on it? If not – you’re in good company. MOST people haven’t worked through that derivation – and for good reason. MOST people don’t remember their chain rule methods from first semester calculus. (It probably doesn’t help if I say that the backprop…
Picking up from our conversation of two weeks ago, we’re continuing to look at the robot Sophia, who is designed to be human-like in facial expressions and eye contact. Sophia can converse easily with you in a natural-speaking voice. She’s a far cry from the stiff and stern robots (with their monotonic voices) that have been portrayed in many (in-the-past) movies and TV shows. At the same time, while the YouTube interviews with Sophia give us the sense that she…
Emotional AI – which has been around for several years – is likely to surge forward over the next 3-5 years, creating several new market niches. First, Some Background The leading avatar for emotional AI is the robot Sophia, developed by Hanson Robotics Limited. Sophia has been around since 2017, and improves every year. Hanson Robotics describes their robots as having ” good aesthetic design, rich personalities, and social cognitive intelligence [that] can potentially connect deeply and meaningfully with humans.”…
When students run neural networks code, one of the first things that gets their attention is the summed-squared-error (SSE) – at the beginning of the run (before training), and then again after training has been done for several thousands of iterations. There are usually three basic questions that people ask about SSE, with regard to a particular neural network: I’ve got an SSE value taken before my neural network starts training. Does this value make sense? My neural network has…
Thrilled that so many of you are showing an interest in my book-in-progress, Statistical Mechanics, Neural Networks, and Artificial Intelligence. Since I’m putting draft chapters up on this website (even if they’re still a bit rough – like not having all the parts in place yet), you’re getting access to the full book-in-progress. That said, some of you who are newer to this community are wondering where some of the early chapters are, as witnessed by this — Question from…
One of my favorite colleagues rereads Sun Tzu’s The Art of War every year. Just so he doesn’t forget the important points. Keep it fresh, so to speak. And yesterday, I took a break from working on my most recent chapter draft to order different versions and interpretations of Sun Tzu’s famous classic. Why? Because I realized that I didn’t really know the ground that I was standing on. Not literally, of course. I know where I’m living in the…
“AI at the Edge” – coming soon to a theater near you! OK. Maybe not to a theater. But most certainly, a live webinar (where you can offer questions during the live Q&A at the end), to be hosted by Avnet on Thursday, Dec. 5th, 2PM EST. (Don’t worry; I’ll send out reminders.) Why “AI at the Edge”? And Why Now? You know that I’m mostly a theoretician. (Love ’em equations.) So for me to go over to the dark…
He might be getting a Nobel prize some day. But – no one can understand him. You don’t believe me? Have a quick glance at Scott Alexander’s article, “God Help Us, Let’s Try To Understand Friston On Free Energy”. We’re referring, of course, to Karl Friston. I’ve spent the past three-and-a-half years studying Friston’s approach to free energy, which he treats as the guiding principle in the brain. He has extended the classic variational Bayes treatment (frontier-material in machine learning)…
Most of us don’t always use graph language to describe neural networks, but if we dig into the implications of graph theory language, we get some surprising (and very useful) insights! We probably all know that a typical feedforward neural network can be described as a “directed graph.” Many of us also know that a restricted Boltzmann machine (RBM) is an “undirected graph.” In this little difference of terms, there is a wealth of meaning. Salakhutdinov, Mnih, and Hinton (2007;…