Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate,regime transitions, and the effect of stochasticity

2021 ◽  
Vol 31 (3) ◽  
pp. 033149
Author(s):  
Dhruvit Patel ◽  
Daniel Canaday ◽  
Michelle Girvan ◽  
Andrew Pomerance ◽  
Edward Ott
Keyword(s):  
Machine Learning ◽  
Statistical Properties ◽  
Climate Regime ◽  
Dynamical Processes ◽  
Regime Transitions

A new generic method to improve machine learning applications in official statistics

2021 ◽  
pp. 1-16
Author(s):  
Kevin Kloos
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Statistical Properties ◽  
Machine Learning Algorithms ◽  
Official Statistics ◽  
Academic Literature ◽  
Misclassification Bias ◽  
Squared Error ◽  
Machine Learning Applications ◽  
Applications Of Machine Learning

The use of machine learning algorithms at national statistical institutes has increased significantly over the past few years. Applications range from new imputation schemes to new statistical output based entirely on machine learning. The results are promising, but recent studies have shown that the use of machine learning in official statistics always introduces a bias, known as misclassification bias. Misclassification bias does not occur in traditional applications of machine learning and therefore it has received little attention in the academic literature. In earlier work, we have collected existing methods that are able to correct misclassification bias. We have compared their statistical properties, including bias, variance and mean squared error. In this paper, we present a new generic method to correct misclassification bias for time series and we derive its statistical properties. Moreover, we show numerically that it has a lower mean squared error than the existing alternatives in a wide variety of settings. We believe that our new method may improve machine learning applications in official statistics and we aspire that our work will stimulate further methodological research in this area.

scholarly journals An epistemic approach to the formal specification of statistical machine learning

2020 ◽  
Author(s):  
Yusuke Kawamoto
Keyword(s):  
Machine Learning ◽  
Formal Specification ◽  
Formal Model ◽  
Kripke Model ◽  
Classification Performance ◽  
Statistical Properties ◽  
Statistical Machine Learning ◽  
Possible World ◽  
Starting Point ◽  
Epistemic Approach

Abstract We propose an epistemic approach to formalizing statistical properties of machine learning. Specifically, we introduce a formal model for supervised learning based on a Kripke model where each possible world corresponds to a possible dataset and modal operators are interpreted as transformation and testing on datasets. Then, we formalize various notions of the classification performance, robustness, and fairness of statistical classifiers by using our extension of statistical epistemic logic. In this formalization, we show relationships among properties of classifiers, and relevance between classification performance and robustness. As far as we know, this is the first work that uses epistemic models and logical formulas to express statistical properties of machine learning, and would be a starting point to develop theories of formal specification of machine learning.

Weather Regime Transitions and the Interannual Variability of the North Atlantic Oscillation. Part II: Dynamical Processes

2012 ◽  
Vol 69 (8) ◽  
pp. 2347-2363 ◽  
Author(s):  
Dehai Luo ◽  
Jing Cha ◽  
Steven B. Feldstein
Keyword(s):  
North Atlantic Oscillation ◽  
North Atlantic ◽  
Large Scale ◽  
Storm Track ◽  
Constructive Interference ◽  
Dynamical Processes ◽  
The North ◽  
The North Atlantic ◽  
The North Atlantic Oscillation ◽  
Regime Transitions

Abstract In this study, attention is focused on identifying the dynamical processes that contribute to the negative North Atlantic Oscillation (NAO)− to positive NAO (NAO+) and NAO+ to NAO− transitions that occur during 1978–90 (P1) and 1991–2008 (P2). By constructing Atlantic ridge (AR) and Scandinavian blocking (SBL) indices, the composite analysis demonstrates that in a stronger AR (SBL) winter NAO− (NAO+) event can more easily transition into an NAO+ (NAO−) event. Composites of 300-hPa geopotential height anomalies for the NAO− to NAO+ and NAO+ to NAO− transition events during P1 and P2 are calculated. It is shown for P2 (P1) that the NAO+ to SBL to NAO− (NAO− to AR to NAO+) transition results from the retrograde drift of an enhanced high-latitude, large-scale, positive (negative) anomaly over northern Europe during the decay of the previous NAO+ (NAO−) event. This finding cannot be detected for NAO events without transition. Moreover, it is found that the amplification of retrograding wavenumber 1 is more important for the NAO− to NAO+ transition during P1, but the marked reintensification and retrograde movement of both wavenumbers 1 and 2 after the NAO+ event decays is crucial for the NAO+ to NAO− transition during P2. It is further shown that destructive (constructive) interference between wavenumbers 1 and 2 over the North Atlantic during P1 (P2) is responsible for the subsequent weak NAO+ (strong NAO−) anomaly associated with the NAO− to NAO+ (NAO+ to NAO−) transition. Also, the weakening (strengthening) of the vertically integrated zonal wind (upstream Atlantic storm track) is found to play an important role in the NAO regime transition.

Mind wandering as data augmentation: How mental travel supports abstraction

2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Mental Content ◽  
Mind Wandering ◽  
Theoretical Framework ◽  
Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Data Mining and Machine Learning

2020 ◽  
Author(s):  
Mohammed J. Zaki ◽  
Wagner Meira, Jr
Keyword(s):  
Machine Learning ◽  
Data Mining
Sign in / Sign up

Export Citation Format

Share Document