you are not logged in, login. new entry
text: sort by
tags: modified
type: chronology
hide / edit[0] / print
ref: -0 tags: variational free energy inference learning bayes curiosity insight date: 10-31-2018 22:33 gmt revision:0 [head]

Active inference, curiosity and insight.

  • This has been my intuition for a while; you can learn abstract rules via active probing of the environment. This paper supports such intuitions with extensive scholarship.
  • “The basic theme of this article is that one can cast learning, inference, and decision making as processes that resolve uncertanty about the world.
    • References Schmidhuber 1991
  • “A learner should choose a policy that also maximizes the learner’s predictive power. This makes the world both interesting and exploitable.” (Still and Precup 2012)
  • “Our approach rests on the free energy principle, which asserts that any sentient creature must minimize the entropy of its sensory exchanges with the world.” Ok, that might be generalizing things too far..
  • Levels of uncertainty:
    • Perceptual inference, the causes of sensory outcomes under a particular policy
    • Uncertainty about policies or about future states of the world, outcomes, and the probabilistic contingencies that bind them.
  • For the last element (probabilistic contingencies between the world and outcomes), they employ Bayesian model selection / Bayesian model reduction
    • Can occur not only on the data, but exclusively on the initial model itself.
    • “We use simulations of abstract rule learning to show that context-sensitive contingiencies, which are manifest in a high-dimensional space of latent or hidden states, can be learned with straightforward variational principles (ie. minimization of free energy).
  • Assume that initial states and state transitions are known.
  • Perception or inference about hidden states (i.e. state estimation) corresponds to inverting a generative model gievn a sequence of outcomes, while learning involves updating the parameters of the model.
  • The actual task is quite simple: central fixation leads to a color cue. The cue + peripheral color determines either which way to saccade.
  • Gestalt: Good intuitions, but I’m left with the impression that the authors overexplain and / or make the description more complicated that it need be.
    • The actual number of parameters to to be inferred is rather small -- 3 states in 4 (?) dimensions, and these parameters are not hard to learn by minimizing the variational free energy:
    • F=D[Q(x)P(x)]E q[ln(P(o tx)] where D is the Kullback-Leibler divergence.
      • Mean field approximation: Q(x) is fully factored (not here). many more notes

hide / edit[0] / print
ref: -0 tags: polyimide adhesion oxygen nitrogen plasma surface energy date: 03-10-2014 22:33 gmt revision:0 [head]

Adhesion Properties of Electroless-Plated Cu Layers on Polyimide Treated by Inductively Coupled Plasmas

  • O2 then N2/H2 ICP treatment of polyimide surfaces dramatically lowers the surface energy (as measured by contact angle), and increases the adhesion of palladium-catalyzed electroless copper.
  • Particularly, C-N bonds are increased as revealed by XPS.
  • No peel-strength measurements given.

hide / edit[2] / print
ref: -0 tags: bees energy harvesting honey date: 04-11-2012 06:02 gmt revision:2 [1] [0] [head]

This morning hundreds of bees were swarming outside my front door -- a fact is not without reason, as my roommate makes honey, and her hive just today outgrew the apiary. Hence the hive split this morning, and one queen be left to wait on a branch outside while scouts searched for good places to build a new colony; meanwhile hundreds of non-scout workers were swarming around her.

Bees are amazing. Anyway, a friend sent a link to an article describing how to generate microwatts of energy off a flying insect, which led me to wonder how much energy those bees could have been producing instead of milling protectively about their queen.

  • number of bees : 1000
  • power, with direct connection to flight muscles: 400 uW
  • total possible power: 400mW
  • kCal in a tablespoon (21g) of honey: 64
    • in joules: 270kJ
  • Length of time it would take for 500 madly flapping bees (1) to generate the energy within a tablespoon of honey: 375 hours (15.6 days)
  • Yield of honey from a large, productive hive: 150 lbs / year (2)
    • in watts: 27.8 W
    • number of bees: 20000 (2)
    • factor better than energy harvesting: 3.5

Conclusion: let them make honey :-)

(1) Half the bees visible were resting on leaves, not madly flapping.

(2) Rough wiki-google estimate.

hide / edit[2] / print
ref: Friston-2010.02 tags: free energy minimization life learning large theories date: 06-08-2010 13:59 gmt revision:2 [1] [0] [head]

My letter to a friend regarding images/817_1.pdf The free-energy principle: a unified brain theory? PMID-20068583 -- like all critics, i feel the world will benefit from my criticism ;-) Hey , I did read that paper on the plane, and wrote down some comments, but haven't had a chance to actually send them until now. err..anyway.. might as well send them since I did bother writing stuff down: I thought the paper was interesting, but rather specious, especially the way the author makes 'surprise' something to be minimized. This is blatantly false! Humans and other mammals (at least) like being surprised (in the normal meaning of the word). He says things like: "This is where free energy comes in: free energy is an upper bound on surprise, which means that if agents minimize free energy, they implicity minimize surprise -- a huge logical jump, and not one that I'm willing to accept. I feel like this author is trying to capitalize on some recent developments, like variational bayes and ensemble learning, without fully understanding them or having the mathematical chops (like Hayen) to flesh it out. So far as I understand, large theories (as this proposes to be) are useful in that they permit derivation of particular update equations; Variational Bayes for example takes the Kullbeck-Leibler divergence & a factorization of the posterior to create EM update equations. So, even if the free energy idea is valid, the author uses it at such a level to make no useful, mathy predictions. One area where I agree with him is that the nervous system create a model of the internal world, for the purpose of prediction. Yes, maybe this allows 'surprise' to be minimized. But animals minimize surprise not because of free energy, but rather for the much more quotidian reason that surprise can be dangerous. Finally, i wholly reject the idea that value and surprise can be equated or even similar. They seem orthogonal to me! Value is assigned to things that help an animal survive and multiply, surprise is things it's nervous system does not expect. All these things make sense when cast against the theories of evolurion and selection. Perhaps, perhaps selection is a consequence of decreasing free energy - this intuitively and somewhat amorphously/mystically makes sense (the aggregate consequence of life on earth is somehow order, harmony and other 'goodstuff' (but this is an anthropocentric view)) - but if so the author should be able to make more coherent / mathematical prediction of observed phenomena. Eg. why animals locally violate the second law of thermodynamics. Despite my critique, thanks for sending the article, made me think. Maybe you don't want to read it now and I saved you some time ;-)

hide / edit[1] / print
ref: -0 tags: cost of energy renewable date: 06-11-2009 12:33 gmt revision:1 [0] [head]

Gleaned from the Economist (June 6-12 2009) "

photovoltaic cells$0.56
natural gas$0.08

Italy imports 86% of it's electricity (!)

hide / edit[2] / print
ref: notes-0 tags: energy carbon CO2 hot water heater. date: 02-25-2008 23:36 gmt revision:2 [1] [0] [head]

How much carbon dioxide (CO2) is released to heat the water for a 5-minute shower?

  1. assumptions
    1. water enters your house at 45F, and you heat it to 100F.
    2. the energy efficiency of your hot water heater is 87%, and we ignore the cost of static thermal losses.
    3. you live in the southeast like me, which is predominantly powered by coal-fired plants. These plants release about 0.8kg/kwh of CO2 ref
    4. transmission of energy from the power plant to your home is 90% efficient
    5. you have a shower head that flows at a rate of 2.2 gallons/minute
  2. result: 2.2gpm -> 138.6 ml/sec -> * 31C temp rise -> 4.2kw -> 0.31kg CO2.
    1. that's about equivalent of driving 4 miles in a 30mpg car. (gasoline CO2 release = 2.4kg/gallon)

  • Interesting analysis. I'm surprised how much CO2 is used by those 5-minutes of delicious, delicious hot shower! --joeyo