DR.GEEK
Stanford NER Version 3.8.0 Setup
(19th-January-2021) • Let’s start the setup process. • First download Stanford NER version 3.8.0 using the link provided in previous...
top of page
Search
DR.GEEK
NLP Subtasks
(18th-January-2021) • NLP stands for Natural Language Processing and is related to computer processing of human languages like English •...
DR.GEEK
When Is the Most Likely Finite Stochastic Model the True Model?
(17th-January-2021) • In probability theory and related fields, a stochastic or random process is a mathematical object usually defined...
DR.GEEK
Learning Finite Stochastic Models
(16th-January-2021) • While Hutter studied using MDPs (Hutter 2009a) and dynamic Bayesian networks (DBN) (Hutter 2009b; Ghahramani 1997)...
DR.GEEK
A simplified example of a Markov decision process (MDP)
(15th-January-2021) • A simplified example of a Markov decision process (MDP), not showing outputs. There are three states, S1, S2, and...
DR.GEEK
AI in Our Finite Universe
(14th-January-2021) Universal AI would be computable if it used TMs with finite tapes and the next section will describe a way to do...
DR.GEEK
Block stacking puzzle for Hayek
(13th-January-2021) • The Ethics of Learned Environment Models, For an AI system like Google's self-driving car, the environment model is...
DR.GEEK
Modifications of the Agent Framework
(12th-January-2021) • Universal AI learns an environment model in the form of a probability distribution ρ(h) over interaction histories....
DR.GEEK
A Formal Measure of Intelligence
(11th-January-2021) In addition to its role in defining idealized intelligent agents, Kolmogorov complexity can also be used to define...
DR.GEEK
Universal AI
(10th-January-2021) • Let U be a reference UTM and let Q be the infinite set of all programs for U. These programs are finite bit strings...
DR.GEEK
Utilitarian Ethics for AI
(9th-January-2021) • Utilitarianism is a system of normative ethics that says we should choose actions that maximize benefit and minimize...
DR.GEEK
Each o∈O takes its share ρ(hao) / ∑o'∈O ρ(hao') of the total probability of 1.0.
(8th-January-2021) • Utility-Maximizing Agents • Numerical values assigned to outcomes can express any set of preferences among outcomes...
DR.GEEK
A Mathematical Framework for AI
(7th-January-2021) • A current approach views AI as an agent interacting with an environment (Russell and Norvig 2010; Sutton and Barto,...
DR.GEEK
An AI police officer watching a hitman aim a gun at a victim
(6th-January-2021) • If you try to dig into the details of these tradeoffs, you will end up having to understand the AI's social model....
DR.GEEK
Omniscience AI explaining its social model and CEO throwing up hands
(5th-January-2021) • Humans have created other tools whose unintended consequences are harmful. Drugs can cure infections and ease pain...
DR.GEEK
Self-driving car and its model of the environment
(4th-January-2021) • In the future when everyone has a constant electronic companion with which they can speak. It may be embodied in a...
DR.GEEK
Future AI Will be Different from Current AI
(3rd-January-2021) • What is the future of AI? IBM's Watson beat champions of the sophisticated language game Jeopardy. • April 2014...
DR.GEEK
AI cognitive science model
(2nd-January-2021) • Today, we describe how numerical values assigned to outcomes fit into a mathematical framework for the way that AI...
DR.GEEK
Overfitting
(1st-January-2021) Original purpose of machine learning Classifying unknown input correctly It is not to classify learning cases...
DR.GEEK
Information Gain example
(31th-December-2020) The example of information gain are followings. Attribute to split Here is Branching by Outlook attribute.
bottom of page