“What my deep model doesn’t know...” (Something of a tour de force: isomorphism between Gaussian processes and deep neural networks showing dropout is equivalent to using 1 NN to average over a whole family of similar models (explaining why dropout improves results, since we all know the advantages of ensembles) and showing how variation in NN output when wiggled by dropout gives an indication of uncertainty in predictions and from there yields useful results and stuff like usable Thompson sampling (!) in the famous deep Q reinforcement-learner for optimizing exploration and learning faster. Phew.)
Everything is heritable:
“Genetic and environmental determinants of violence risk in psychotic disorders: a multivariate quantitative genetic study of 1.8 million Swedish twins and siblings”, Sariaslan et al 2015 (Genetic pleiotropy/confounding in schizophrenia & drug abuse, rather than causation or reverse causation?)
“Systems genetics identifies a convergent gene network for cognition and neurodevelopmental disease”, Johnson et al 2015 (media)
on the benefits of exercise:
“Modifiable Risk Factors as Predictors of All-Cause Mortality: The Roles of Genetics and Childhood Environment”, Kujala et al 2002
“Physical activity in adulthood: genes and mortality”, Karvinen et al 2015
“Physical Activity, Fitness, Glucose Homeostasis, and Brain Morphology in Twins”, Rottensteiner et al 2015 (commentary)
“How Much Can We Boost IQ and Scholastic Achievement?”, Jensen 1969
Politics/religion:
“Operation Easy Chair, or how a little company in Holland helped the CIA bug the Russians”
“The Life Issue”/”What if drone warfare had come first?”
“‘Perplexed … Perplexed’: On Mob Justice in Nigeria”
Statistics/AI/meta-science:
“What my deep model doesn’t know...” (Something of a tour de force: isomorphism between Gaussian processes and deep neural networks showing dropout is equivalent to using 1 NN to average over a whole family of similar models (explaining why dropout improves results, since we all know the advantages of ensembles) and showing how variation in NN output when wiggled by dropout gives an indication of uncertainty in predictions and from there yields useful results and stuff like usable Thompson sampling (!) in the famous deep Q reinforcement-learner for optimizing exploration and learning faster. Phew.)
“On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models” (AIT is usually too hopelessly abstract and general to apply to anything, but Schmidhuber gets inspiration for some interesting architectures from it.)
“The Endogeneity Problem in Developmental Studies”, Duncan et al 2004 (How often does correlation=causation? More examples.)
″...a list of thirty four Nobel Laureates whose awarded work was rejected by peer review.”
“The Use and Abuse of Transcranial Magnetic Stimulation to Modulate Corticospinal Excitability in Humans”, Heroux et al 2014
Psychology/biology:
“A Look Back at 2015 in Longevity Science”
“Safety Lessons From the Morgue”
“Adolescent sleep and fluid intelligence performance”, Johnstone et al 2010
Technology:
Archaeoacoustics: “Scientists Recover the Sounds of 19th-Century Music and Laughter From the Oldest Playable American Recording”
“Computer-related accidental death: an empirical exploration”, MacKenzie 1994
Experimental History
Economics:
“The financing of jihadi terrorist cells in Europe”, Oftedal 2015
“How persuasive are open borders advocates? The case of Bryan Caplan”
Tableau économique
Fiction:
“The Argentine Writer and Tradition”, Borges 1951
“Axe Handles”, Gary Snyder
“Back from yet another globetrotting adventure, Indiana Jones checks his mail and discovers that his bid for tenure has been denied”
Misc:
“The Bonsai Kid”