The Hierarchical Temporal Memory (HTM) theory of cognition

In the article Why Can’t A Computer Be More Like A Brain? (spectrum.ieee.org) author Jeff Hawkins proposes a theory of how the brain works and how it could be implemented in computers:

“Memory of what a dog looks like is not stored in one location. Low-level visual details such as fur, ears, and eyes are stored in low-level nodes, and high-level structure, such as head or torso, are stored in higher-level nodes.the low-level nodes learn first. Representations in high-level nodes then share what was previously learned in low-level nodes.

each node in the hierarchy learns common, sequential patterns, analogous to learning a melody. When a new sequence comes along, the [lower level] node matches the input to previously learned patterns, analogous to recognizing a melody. Then the [lower level] node outputs a constant pattern representing the best matched sequences, analogous to naming a melody. Given that the output of nodes at one [lower] level becomes input to nodes at the next [higher] level, the hierarchy learns sequences of sequences of sequences.”

A graphic (PDF) from the article demonstrates the point:

What the article sort of talks about is the intrinsic role of time based feedback loops as part of how a node recognizes a pattern. I’m guessing that rather than process a wide bit pattern directly, “nodes” process the wide bit pattern in chunks remembering the node’s state based on the previous sequence of chunks and determining the new state based on the previous state and the current new chunk (and maybe neighboring/parent node states)

The Limited Importance of Process Maturity in Software Development

An article by Steve McConnell from IEEESoftware.com notes that, surprisingly, software development process maturity (ie., rigorous technical management procedures) doesn’t seem to matter as much as “soft” factors like: seniority of personnel, good communication, motivation, analyst experience, etc.

The unstated implication is that the academics and big corporations concentrate too much on process maturity (eg. ISO 9001 & CMMI), because that’s easy to quantify, rather than actually being important.

Bizarre humorous personal ads from London Review of Books

In the London Review of Books personal ads, self deprecating humor is apparently the fashion. My favorite is:

I like my women the way I like my kebab. Found by surprise after a drunken night out, and covered in too much tahini. Before long I’ll have discarded you on the pavement of life, but until then you’re the perfect complement to a perfect evening. Man, 32. Rarely produces winning metaphors.

The title comes from the personals ad:

They call me Naughty Lola. Run of the mill beardy physicist — male, 46.

Continue reading “Bizarre humorous personal ads from London Review of Books”

My WashPost letter to the editor: Don’t blame the military for the Iraq fiasco

From my letter to the editor in the 10/30/06 Washington Post, in response to the editorial Insult to Injury in Iraq by Frederick W. Kagan (resident scholar/conservative hack at the American Enterprise Institute):

In his op-ed, Insult to Injury in Iraq, Frederick W. Kagan blames the U.S. military for the Iraq fiasco, saying that Central Command “never actually made establishing order and security a priority.”But wasn’t it Defense Secretary Donald H. Rumsfeld who threatened to fire anyone who brought up the subject of “post-invasion operations” (also known as nation building) in Iraq? And wasn’t it the Bush administration’s aversion to nation building that limited our postwar options?

Mr. Kagan shouldn’t blame the military for following orders.

I wrote this because nobody in the Washington Post seemed to be making a distinction between the military and the ideologically driven agenda of the Bush administration. More people need to do so.

The Twelve Tribes of American Politics

From The Atlantic Monthly: A chart which breaks the 2004 electorate into twelve politically relevant “tribes” based on their values, behaviors, and religious affiliation. Each circle corresponds in relative size to the group it represents. The chart reveals some polarization of the electorate. But it also shows that voting preferences do not sort as neatly by cultural values or religious affiliation as people might expect:

Object oriented design lesson: Control flow should not be a class behavior

From an article in the journal IEEE Software, May 1996, page 37. Unfortunately, I don’t have the author or title of the article and searches for the content on ieee.org don’t seem to find it, so I’ve scanned it in below.

Although most of the software world doesn’t seem to talk about OOD this way, the “lesson” below seems reasonable based on my experiences.

If the control flow is partitioned into a “separate dynamic control flow object” as mentioned below, isn’t that object really not an object at all, based on the definition of an object containing data and actions modelling an entity? Stated another way, object oriented design only makes sense when the actions are centered around a piece of data. In this case, the actions are centered around coordinating control flow.

Could the whole computer science industry be so wrong about something for so long? I seems similar to the repudiation of psychoanalysis after 60 years of the dominance of the theory:

Continue reading “Object oriented design lesson: Control flow should not be a class behavior”