Everything net
Everything relevant to the thought
... One use of Twitter: to post background information that I may use in columns and newsletters. So, a bit about market expectations of inflation. Right now, the yield on one-year inflation-protected Treasuries is -3.2% 1/ https://t.co/fl2zU5H36X The one-year rate on ordinary Treasuries is 0.48%. ...
1486 characters.
... We do so by examining the cognitive abilities associated with three contemporary theories of conscious function: Global Workspace Theory (GWT), Information Generation Theory (IGT), and Attention Schema Theory (AST). ...
... With this insight, we turn to the field of Artificial Intelligence (AI) and find that, while still far from demonstrating general intelligence, many state-of-the-art deep learning methods have begun to incorporate key aspects of each of the three functional theories. ...
... Given this apparent trend, we use the motivating example of mental time travel in humans to propose ways in which insights from each of the three theories may be combined into a unified model. ...
1330 characters.
... Thread… Here’s my basic understanding of the model: the economy has some industries that are capital intensive and others that are not. When the central bank makes interest rates artificially low, it makes capital investment cheap and skews the economy toward capital intensive sectors. ...
... In the Austrian theory, a recession is a process of resource re-allocation from capital-intensive to capital-light industries. Society needs to produce fewer factories and machine tools and more beer and pairs of pants (or whatever). ...
... In the Austrian theory, it’s important that central banks don’t interrupt this process by pushing interest rates back down to unnaturally low levels, because that interferes with this necessary re-allocation process. Ok so let’s think about 2006 to 2009. ...
... The period through the end of 2007 arguably fits the austrian model. There was arguably over investment in residential home construction. In 2006 and 2007 the home building industry was contracting while other industries were still growing. But in mid 2008, the situation changed. ...
... I can’t figure out how to explain this period with an Austrian model. I don’t see why anyone would consider this kind of mass unemployment necessary or how it set us up for stronger growth later. ...
2948 characters.
... Yes, I know the HODLers see it as a buying opportunity, and they could be right — not doing price predictions, just trying to think this through 1/ First: crypto faithful comparing this to "crypto winter" of 2017-18, which was comparable in percentage terms. ...
1419 characters.
... Where causality comes in is when we venture to model the 1/2 https://t.co/AmgYUOenjq ...
301 characters.
... Then the idea that 1999 and 2006 were driven by unsustainable bubbles, as opposed to just being healthy economic booms, prevented people from recognizing how far the US economy was below potential from 2010 to 2015. ...
1418 characters.
... Cortical columns make classifications based on raw sensory inputs as well as classification signals from other columns. They learn by predicting incoming raw sensory inputs as well as classification signals from other columns. ...
... One column's prediction error helps its own learning, as well as other columns' learning when the prediction was made with input from their classification signals. What do you think of my hypothesis? ...
... **ChatGPT**: Your hypothesis describes a process that is similar to how the brain is thought to process and classify sensory information. Cortical columns, which are groups of neurons in the cerebral cortex, are thought to play a role in processing and classifying sensory information. ...
... They do this by receiving input from sensory organs and then making predictions about what this input represents. These predictions are then compared to the actual input, and any discrepancies between the two are used to update the column's understanding of the sensory information. ...
... It is also thought that cortical columns communicate with each other, sharing information about the sensory input they have received and the predictions they have made. ...
... This can help to improve the overall accuracy of the predictions made by the brain, as different columns may have different strengths and areas of expertise in processing different types of sensory information. ...
... Overall, your hypothesis captures some of the key principles of how the brain processes and classifies sensory information, and it is generally consistent with current understanding of this process. ...
... However, it is important to note that the brain is a complex and multifaceted organ, and our understanding of how it works is still evolving. There may be additional factors and processes at play that are not captured in your hypothesis. ...
1869 characters.
... Suggested in [Being You](https://www.anilseth.com/being-you/), the perception process is a top-down "controlled hallucination." The brain predicts conceived "things" it will see and then "the sensory input" caused by them. ...
... Then the brain verifies or corrects the conceived things with the sensory input it actually receives. ...
324 characters.
... Because this self-supervised learning process mimics the brain's learning mechanism: make predictions and learn from prediction errors. ...
135 characters.
... The controlled hallucination process is also a hypotheses-prediction-observation correction learning process. Brains can learn brand new concepts by generating new hypotheses about the world, making predictions about the sensory input, and correcting according to observation (actual sensory input) ...
298 characters.
... Human perception is a controlled/controlling hallucination process in which the brain 1\. constantly generates hypotheses of the world around and 2\. makes predictions about incoming sensory signals based on these hypotheses 3\. correct hypotheses according to differences between observations \(actual ...
... sensory signals and predictions\. \) ...
342 characters.
... The brain learns by constantly making predictions and making corrections (in its wiring) to approach close to the actual results. ...
129 characters.