discipline

Table of Contents

Discipline is an abstraction of grouping related ideas together, usually seen in academic context, like “machine learning” would comprise “function approaximisation”, “linear ”(that thing with statistics), “neural network” and many other ideas.

Backlinks

Linfeng He, as I live and breath…

My name is Linfeng He, and I live by my university in Liverpool, UK.

My alias online follows a common structure of herman[n][he[l[f]]], so HErman, herman, hermann, hermanhe, heramnnhelf... They stems out from my “English name” used in primary English classroom, which my dad had given me primarily for my last name’s He. (which makes no sense, as his last name is He too)

I’m now a Computer Science student in my final year of Bachelor, and apart from that mostly an enthusiast: I’m interested in many things, and believes in the distributed nature of discipline that all those many things I read, thought, and wrote about would constitute this one unique field of mine. Here’s a list of many things:

  • artificial general intelligence, or artificial child(people often refer to it as “it learns like how babies learn”).
  • robotics
  • programming
  • math, especially logic and symbolic representation(formal method, modal logic, language theory…)
  • process/system design (hack as in life hack, lifestyle)
  • illustration
  • music, composing, musical theatre
  • jazz piano
  • cooking and eating
  • meditation
  • philosophy, my likings are some parts of Nietzsche’s school(more or less), and some part of skepticism
  • fiction
  • essay and academic discussion
  • scholar tradition (I sort of invented it myself anyway, but I’d like to think that by joining uni, I’m following the scholar tradition that goes all the way back to ancient greek folks like Pyrrho of Elis)

developmental skill aquisition with general purpose actuator

(Introduction)

Developmental Learning/Developmental Robotics is a machine learning method with focus on automatic knowledge development. The core tension of the method is to let agent autonomously construct knowledge and self-programme, base on experiences/experiments of their interactions with the world. The method take inspiration from children’s cognitive development. inapp On the various definitions and properties of Artificial General Intelligence, one is the ability to develop, autonomously, knowledge/internal representations that is effectively incremental, meaning that the agent should be able to acquire new knowledge and new skills of new subject domain all by itself, with as little friction across boundaries of disciplines as possible. Developmental Learning is one paradigm of such.

There are mainly 2 lines of works on this subject, one focuses on modelling infant’s cognitive development and the other focuses on development of agent with analogies/features from cognitive development and approaches from computer science and machine learning.

On the infant line, visual signal processing, eye-gaze tracking are normally present, while on the robotics line, general purpose actuator like arm and wheel, and skill acquisition with those actuators are nomrally present.

This work would aim at evaluating and developing developmental learning schemes and their application on general purpose actuators such as robotic arm, in pursuit of a learning scheme that is general-applicable(architecture-free) and can let agent effectively acquire new skill with a pre-defined, finite set of actuators or actions.

Author: Linfeng He

Created: 2024-04-03 Wed 23:22