background preloader

Cognitive bias

Cognitive bias
Systematic pattern of deviation from norm or rationality in judgment A continually evolving list of cognitive biases has been identified over the last six decades of research on human judgment and decision-making in cognitive science, social psychology, and behavioral economics. The study of cognitive biases has practical implications for areas including clinical judgment, entrepreneurship, finance, and management.[10][11] The notion of cognitive biases was introduced by Amos Tversky and Daniel Kahneman in 1972[12] and grew out of their experience of people's innumeracy, or inability to reason intuitively with the greater orders of magnitude. The "Linda Problem" illustrates the representativeness heuristic (Tversky & Kahneman, 1983[14]). Critics of Kahneman and Tversky, such as Gerd Gigerenzer, alternatively argued that heuristics should not lead us to conceive of human thinking as riddled with irrational cognitive biases. Biases can be distinguished on a number of dimensions. [edit] Related:  Cognitive Bias & Logical Fallacies

What Is a Cognitive Bias? When we are making judgments and decisions about the world around us, we like to think that we are objective, logical, and capable of taking in and evaluating all the information that is available to us. The reality is, however, that our judgments and decisions are often riddled with errors and influenced by a wide variety of biases. The human brain is both remarkable and powerful, but certainly subject to limitations. One type of fundamental limitation on human thinking is known as a cognitive bias. A cognitive bias is a type of error in thinking that occurs when people are processing and interpreting information in the world around them. Cognitive biases can be caused by a number of different things. These biases are not necessarily all bad, however. Cognitive Bias vs. People sometimes confuse cognitive biases with logical fallacies, but the two are not the same. A Few Types of Cognitive Biases More Psychology Definitions: The Psychology Dictionary Browse the Psychology Dictionary

Inductive bias From Wikipedia, the free encyclopedia Assumptions for inference in machine learning The inductive bias (also known as learning bias) of a learning algorithm is the set of assumptions that the learner uses to predict outputs of given inputs that it has not encountered.[1] Inductive bias is anything which makes the algorithm learn one pattern instead of another pattern (e.g. step-functions in decision trees instead of continuous function in a linear regression model). In machine learning, one aims to construct algorithms that are able to learn to predict a certain target output. A classical example of an inductive bias is Occam's razor, assuming that the simplest consistent hypothesis about the target function is actually the best. Approaches to a more formal definition of inductive bias are based on mathematical logic. Types[edit] The following is a list of common inductive biases in machine learning algorithms. Shift of bias[edit] See also[edit] References[edit]

List of cognitive biases Systematic patterns of deviation from norm or rationality in judgment Cognitive biases are systematic patterns of deviation from norm and/or rationality in judgment. They are often studied in psychology, sociology and behavioral economics.[1] Although the reality of most of these biases is confirmed by reproducible research,[2][3] there are often controversies about how to classify these biases or how to explain them.[4] Several theoretical causes are known for some cognitive biases, which provides a classification of biases by their common generative mechanism (such as noisy information-processing[5]). Gerd Gigerenzer has criticized the framing of cognitive biases as errors in judgment, and favors interpreting them as arising from rational deviations from logical thought.[6] Explanations include information-processing rules (i.e., mental shortcuts), called heuristics, that the brain uses to produce decisions or judgments. Belief, decision-making and behavioral[edit] Anchoring bias[edit]

No free lunch in search and optimization Average solution cost is the same with any method The problem is to rapidly find a solution among candidates a, b, and c that is as good as any other, where goodness is either 0 or 1. There are eight instances ("lunch plates") fxyz of the problem, where x,y, and z indicate the goodness of a, b, and c, respectively. In the "no free lunch" metaphor, each "restaurant" (problem-solving procedure) has a "menu" associating each "lunch plate" (problem) with a "price" (the performance of the procedure in solving the problem). Overview[edit] "The 'no free lunch' theorem of Wolpert and Macready," as stated in plain language by Wolpert and Macready themselves, is that "any two algorithms are equivalent when their performance is averaged across all possible problems To make matters more concrete, consider an optimization practitioner confronted with a problem. Theorems[edit] A "problem" is, more formally, an objective function that associates candidate solutions with goodness values. . and Origin[edit]

Being Really, Really, Ridiculously Good Looking “I’m pretty sure there’s a lot more to life than being really, really, ridiculously good looking. And I plan on finding out what that is.”~Derek Zoolander, Zoolander Humans like attractive people. Those blessed with the leading man looks of Brad Pitt or the curves of Beyonce can expect to make, on average, 10% to 15% more money over the course of their life than their more homely friends. This insight is not lost on Madison Avenue or Hollywood. Abercrombie & Fitch might be able to sell more clothes by having good-looking sales associates, but is that legal? The surprising answer is none. Is that a problem? The Science of Beauty Beauty is often considered subjective and “in the eye of the beholder.” To some extent this is true. However, academic work on beauty finds that much of what we find attractive is consistent over time and across cultures. More evidence of a universal, objective basis for beauty comes from studies of babies presented with pictures of different faces. The Halo Effect

Algorithmic bias Technological phenomenon with social implications Algorithmic bias describes systematic and repeatable errors in a computer system that create "unfair" outcomes, such as "privileging" one category over another in ways different from the intended function of the algorithm. Bias can emerge from many factors, including but not limited to the design of the algorithm or the unintended or unanticipated use or decisions relating to the way data is coded, collected, selected or used to train the algorithm. For example, algorithmic bias has been observed in search engine results and social media platforms. This bias can have impacts ranging from inadvertent privacy violations to reinforcing social biases of race, gender, sexuality, and ethnicity. As algorithms expand their ability to organize society, politics, institutions, and behavior, sociologists have become concerned with the ways in which unanticipated output and manipulation of data can impact the physical world. Definitions[edit]

Why You’re Biased About Being Biased In a classic experiment in 1953, students spent an hour doing repetitive, monotonous tasks, such as rotating square pegs a quarter turn, again and again. Then the experimenters asked the students to persuade someone else that this mind-numbing experience was in fact interesting. Some students got $1 ($9 today) to tell this fib while others got $20 ($176 today). According to the researchers, psychologists Merrill Carlsmith and Leon Festinger, this attitude shift was caused by “cognitive dissonance,” the discomfort we feel when we try to hold two contradictory ideas or beliefs at the same time. Scientists have uncovered more than 50 biases that, like this one, can mess with our thinking. Such biases can still affect you even if you know all about them because they operate unconsciously. As much as we may want to believe that thinking positively will lead to positive outcomes, the opposite might be true.

Curse of dimensionality Difficulties arising when analyzing data with many aspects ("dimensions") The curse of dimensionality refers to various phenomena that arise when analyzing and organizing data in high-dimensional spaces that do not occur in low-dimensional settings such as the three-dimensional physical space of everyday experience. The expression was coined by Richard E. Bellman when considering problems in dynamic programming.[1][2] The curse generally refers to issues that arise when the number of datapoints is small (in a suitably defined sense) relative to the intrinsic dimension of the data. Domains[edit] Combinatorics[edit] In some problems, each variable can take one of several discrete values, or the range of possible values is divided to give a finite number of possibilities. binary variables, the number of possible combinations already is , exponential in the dimensionality. Sampling[edit] Optimization[edit] Machine learning[edit] Data mining[edit] Distance function[edit] and dimension , where . as .

Related: