Live data from Hacker News

Viewing profile — atschantz

atschantz

HN member
Joined
Tue, Nov 20, 2018, 5:13 PM UTC
HN karma
37
Public activity
14 items

About atschantz

No profile information was provided.

Recent public activity

  1. comment
    Comment #18907439

    It's remarkable how much this still rings true today. The idea that we should try and understand life as a battle against the second law of thermodynamics has had a significant inf…

  2. comment
    Comment #18907321

    I previously tried to sign up via a Google account but it required a 'company Google account' - I was slightly confused about the reasoning behind this.

  3. comment
    Comment #18906276

    I used Notion for a significant period but ended up switching to Nuclino [1] - which is identical in many respects, but without the various add-ons that are unnecessary if you're w…

  4. comment
    Comment #18720107

    I mean it's difficult to 'observe' gradient descent, there are no characteristic properties that you can identify without specifying the relative objective function. But most of th…

  5. comment
    Comment #18501666

    As a general answer, the theory suggests that organisms maximize a quantity known as model evidence, which is just a way of saying 'how much evidence does some data provide for my …

  6. comment
    Comment #18496568

    I think you might be right, a quote from Friston on the relationship (in reference to belief propagation): "We turn to the equivalent message passing for continuous variables, whic…

  7. comment
    Comment #18496465

    Some attempts have been made in the form of Bayesian model reduction [1]. The idea is to 'carve' out the structure of your model using free energy minimization. [1] https://arxiv.o…

  8. comment
    Comment #18496351

    The idea is that you learn a model by calculating the derivative of free energy with respect to your model parameters.

  9. comment
    Comment #18496062

    It's worth noting that 'free energy' is just the 'evidence lower bound' that is optimized by a large portion of today's machine learning algorithms (i.e. variational auto-encoders)…

  10. comment
    Comment #18495724

    The particular study cited in the article is [1], however for a more general review of the links to reinforcement learning [2]. [1] https://www.biologicalpsychiatrycnni.org/article…

  11. comment
    Comment #18495669

    In terms of the free energy 'principle', it makes no predictions about how free energy minimized. But there have been multiple process theories suggested, most notably predictive c…

  12. comment
    Comment #18495612

    Well, a significant portion of empirical neuroscience works under the assumption that parts of the brain operate according to a predictive coding scheme, and there are countless st…

  13. comment
    Comment #18495534

    There is a large overlap, for instance, the popular VIME exploration algorithm [1] uses part of the free energy objective function. However, free energy isn't a theory of curiosity…

  14. comment
    Comment #18495491

    The 'revolutionary' aspect is the suggestion that a single celled organism is also doing variational inference. Or, more accurately, can be described as such.