I know how egoistic this comment risks sounding, but: many different people (at least half a dozen) have independently expressed to me that they find the links that I post on social media to be consistently interesting and valuable, to the point of one person claiming that about 40% of the value that she got out of Facebook was from reading my posts.
Thus, if you’re not already doing so, you may be interested in following me on social media, either on Facebook or Google Plus. I’m a little picky about accepting friend requests on FB, but anyone is free to follow me there. If you don’t want to be on any of those services, it’s apparently also possible to get an RSS feed of the G+ posts. (I also have a Twitter account, but I use that one a lot less.)
On the other hand, if you’re procrastination-prone, you may want to avoid following me—I’ve also had two people mention that they’ve at least considered unfollowing me because they waste too much time reading my links.
Most Interesting quote I found in first 5 minutes of browsing your G+ feed:
Unfortunately, the bubble was to burst once again, following a series of attacks on connectionism’s representational capabilities and lack of grounding. Connectionist models were criticized for being incapable of capturing the compositionality and productivity characteristic of language processing and other cognitive representations (Fodor & Pylyshyn 1988); for being too opaque (e.g., in the distribution and dynamics of their weights) to offer insight into their own operation, much less that of the brain (Smolensky 1988); and for using learning rules that are biologically implausible and amount to little more than a generalized regression (Crick 1989). The theoretical position underlying connectionism was thus reduced to the vague claim that that the brain can learn through feedback to predict its environment, without a psychological explanation being offered of how it does so. As before, once the excitement over computational power was tempered, the shortage of theoretical substance was exposed.
“One reason that research in connectionism suffered such setbacks is that, although there were undeniably important theoretical contributions made during this time, overall there was insufficient critical evaluation of the nature and validity of the psychological claims underlying the approach. During the initial explosions of connectionist research, not enough effort was spent asking what it would mean for the brain to be fundamentally governed by distributed representations and tuning of association strengths, or which possible specific assumptions within this framework were most consistent with the data. Consequently, when the limitations of the metaphor were brought to light, the field was not prepared with an adequate answer. On the other hand, pointing out the shortcomings of the approach (e.g., Marcus 1998; Pinker & Prince 1988) was productive in the long run, because it focused research on the hard problems. Over the last two decades, attempts to answer these criticisms have led to numerous innovative approaches to computational problems such as object binding (Hummel & Biederman 1992), structured representation (Pollack 1990), recurrent dynamics (Elman 1990), and executive control (e.g., Miller & Cohen 2001; Rougier et al. 2005). At the same time, integration with knowledge of anatomy and physiology has led to much more biologically realistic networks capable of predicting neurological, pharmacological, and lesion data (e.g., Boucher et al. 2007; Frank et al. 2004). As a result, connectionist modeling of cognition has a much firmer grounding than before.”
-- Matt Jones & Bradley C. Love, Bayesian Fundamentalism or Enlightenment? On the explanatory status and theoretical contributions of Bayesian models of cognition.
I would love more detailed/referenced high-level analyses of different approaches to AI (e.g. connectionism v. computationalism v. WBE).
I thought this was an excellent quote from his newsfeed and that it was good evidence that his feed was worth reading. Then, I indirectly asked if he had any similar links/resources, since I thought the quote was so good.
But, really? Is this the most interesting quote you could find in Kaj’s thread? Your quote is long, dry, super-technical, and maybe interesting only to experts. You might argue that the last part carries the general insight that criticism helps the development of new ideas, but it’s still too dense.
To illustrate my point, let me pick a semi-random (I scrolled a bunch randomly and picked without reading) quote from his thread:
Fear of success. At its root this is a fear of change. If I succeed in the thing I am setting out to do, what then? What if I actually become the person I wish to become, who am I? My solution to this was to set up my school and my training in such a way that success was impossible. There is no end goal or end result. There is only process. My mission in life is deliberately unattainable: to restore our European martial heritage to its rightful place at the heart of European culture. Of course that cannot be achieved alone, and there is no reasonable expectation of it being accomplished in my lifetime. There is no question that European martial arts have come a long way in the last decade or so, and my work has been a part of that, but another excellent aspect to this goal is even if we could say it was accomplished in my lifetime, nobody would ever suggest that I did it. So fear of success is not a problem, as success is impossible.
I don’t question that what you quoted would’ve been very interesting for you, but I suspect you’re an expert (or an experienced amateur at least), and I think you underestimated inferential distances.
Thanks! Mind Projection Fallacy on my part. I’m currently trying to pick a topic for my Master’s thesis, and high level overviews of AI-related are very interesting to me.
Likewise, I don’t think that quote is particularly interesting—mainly because I don’t see how I could use it to change my behavior/strategy to achieve my goals.
In summary, Kaj’s feed has interesting information on a wide variety of topics, a subset of which will probably be interesting to many of the people reading this.
I know how egoistic this comment risks sounding, but: many different people (at least half a dozen) have independently expressed to me that they find the links that I post on social media to be consistently interesting and valuable, to the point of one person claiming that about 40% of the value that she got out of Facebook was from reading my posts.
Thus, if you’re not already doing so, you may be interested in following me on social media, either on Facebook or Google Plus. I’m a little picky about accepting friend requests on FB, but anyone is free to follow me there. If you don’t want to be on any of those services, it’s apparently also possible to get an RSS feed of the G+ posts. (I also have a Twitter account, but I use that one a lot less.)
On the other hand, if you’re procrastination-prone, you may want to avoid following me—I’ve also had two people mention that they’ve at least considered unfollowing me because they waste too much time reading my links.
I can confirm that you and gwern are my favourite reads on Google+ (though I don’t visit neither Google+ nor Facebook very often).
I was about to post a comment that said the same!
Most Interesting quote I found in first 5 minutes of browsing your G+ feed:
-- Matt Jones & Bradley C. Love, Bayesian Fundamentalism or Enlightenment? On the explanatory status and theoretical contributions of Bayesian models of cognition.
I would love more detailed/referenced high-level analyses of different approaches to AI (e.g. connectionism v. computationalism v. WBE).
I suppose this would be a good place to start at the very least:
I’m curious why this was down voted.
I thought this was an excellent quote from his newsfeed and that it was good evidence that his feed was worth reading. Then, I indirectly asked if he had any similar links/resources, since I thought the quote was so good.
I didn’t down-vote you.
But, really? Is this the most interesting quote you could find in Kaj’s thread? Your quote is long, dry, super-technical, and maybe interesting only to experts. You might argue that the last part carries the general insight that criticism helps the development of new ideas, but it’s still too dense.
To illustrate my point, let me pick a semi-random (I scrolled a bunch randomly and picked without reading) quote from his thread:
I don’t question that what you quoted would’ve been very interesting for you, but I suspect you’re an expert (or an experienced amateur at least), and I think you underestimated inferential distances.
Thanks! Mind Projection Fallacy on my part. I’m currently trying to pick a topic for my Master’s thesis, and high level overviews of AI-related are very interesting to me.
Likewise, I don’t think that quote is particularly interesting—mainly because I don’t see how I could use it to change my behavior/strategy to achieve my goals.
In summary, Kaj’s feed has interesting information on a wide variety of topics, a subset of which will probably be interesting to many of the people reading this.
Also, I found another similar link on Kaj’s blog: http://kajsotala.fi/2012/09/introduction-to-connectionist-modelling-of-cognitive-processes-a-chapter-by-chapter-review/
I don’t do G+, but can confirm the awesomeness of Kaj’s Facebook feed.