There is no perfect trading system.
I have developed, coded, and tested literally thousands of trading systems. I am not exaggerating. They are all imperfect. Now, I would have always agreed with that on a intellectual level. But I think I did not really “get” that until I had done the work of developing these systems and tested them though various market conditions.
Now I think of systems in terms of yield. A system is not unlike a bond that has a yield that streams off of the instrument itself.
If you like things more literal. Imagine you build windmills. You can maximize efficiency of your blade shape for different speeds and frequency of winds. But one blade will not be efficient in all conditions. Just like a real wind farm, you maximize your blade shape for your prevailing wind condition. If the winds are significantly above or below that condition it is often best to just brake-stop the windmill.
System designers obsess over the shape of their blade, but they often do not think about measuring the conditions in which that blade has maximum efficiency.
Great story. AI is so different from human intelligence it’s really complementary…
Machine Learning’s ‘Amazing’ Ability to Predict Chaos | Quanta Magazine
— Read on www.quantamagazine.org/machine-learnings-amazing-ability-to-predict-chaos-20180418/
Great. Must read…
In an interview, best-selling author and machine-learning expert Pedro Domingos discusses the global competition to take the lead in artificial intelligence, the advance of autocrats and the threats modern technology presents to Western democracies.
— Read on www.spiegel.de/international/world/pedro-domingos-on-the-arms-race-in-artificial-intelligence-a-1203132.html
Great insight here… explains a lot
Talking AI: why selectors trust imperfect humans – Citywire
— Read on citywireselector.com/news/talking-ai-why-selectors-trust-imperfect-humans/a1111267
Very good analysis..
An analysis of more than 400 use cases across 19 industries and nine business functions highlights the broad use and significant economic potential of advanced AI techniques.
— Read on www.mckinsey.com/global-themes/artificial-intelligence/notes-from-the-ai-frontier-applications-and-value-of-deep-learning
The benefits inherent in dramatically-improved medical imaging are huge, and provides examples for similar developments in other industries.
— Read on diginomica.com/2018/04/18/ai-enhanced-instrumentation-fusion-deep-learning-medical-sensors-creates-dramatic-improvements/
This could be a very big deal…
Graphene roll-out combines a roll-to-roll approach — a common industrial approach for continuous processing of thin foils — with the common graphene-fabrication technique of chemical vapor deposition, to manufacture high-quality graphene in large quantities and at a high rate.
— Read on www.techexplorist.com/a-graphene-roll-out/13617/
Expect more of this…
Is the fusion of biology and technology speeding us towards a synthetic future?
— Read on www.bbc.com/news/business-43781851
Flintstones, meet The Flintstones, they’re an AI-generated family. A team of researchers trained an AI to generate video clips from plain language based on an intimate understanding of a classic cartoon.
— Read on thenextweb.com/artificial-intelligence/2018/04/11/researchers-trained-an-ai-to-create-flintstones-cartoons/
Scientists suggest modified CRISPR-RNAs stop the formation of stable zipped conformations on off-target sites and could help improve the safety of CRISPR gene editing.
— Read on www.genengnews.com/gen-news-highlights/crispr-cas9-improved-10000-fold-by-synthetic-nucleotides/81255705
Deep learning: A superhuman way to look at cells
— Read on phys.org/news/2018-04-deep-superhuman-cells.html