Goto

Collaborating Authors

Potential Boosters?

Neural Information Processing Systems

Simply changing the potential function allows one to create new algorithms related to AdaBoost. However, these new algorithms are generally not known to have the formal boosting property. This paper examines the question of which potential functions lead to new algorithms that are boosters. The two main results are general sets of conditions on the potential; one set implies that the resulting algorithm is a booster, while the other implies that the algorithm is not. These conditions are applied to previously studied potential functions, such as those used by LogitBoost and Doom II.


Potential Boosters?

Neural Information Processing Systems

Simply changing the potential function allows one to create new algorithms related to AdaBoost. However, these new algorithms are generally not known to have the formal boosting property. This paper examines the question of which potential functions lead to new algorithms that are boosters. The two main results are general sets of conditions on the potential; one set implies that the resulting algorithm is a booster, while the other implies that the algorithm is not. These conditions are applied to previously studied potential functions, such as those used by LogitBoost and Doom II.


Potential Boosters?

Neural Information Processing Systems

Simply changing the potential function allows one to create new algorithms related toAdaBoost. However, these new algorithms are generally not known to have the formal boosting property. This paper examines thequestion of which potential functions lead to new algorithms thatare boosters. The two main results are general sets of conditions on the potential; one set implies that the resulting algorithm is a booster, while the other implies that the algorithm is not. These conditions are applied to previously studied potential functions, such as those used by LogitBoost and Doom II. 1 Introduction The first boosting algorithm appeared in Rob Schapire's thesis [1].


McKinsey's 2016 Analytics Study Defines The Future Of Machine Learning

Forbes - Tech

Enabling autonomous vehicles and personalizing advertising are two of the highest opportunity use cases for machine learning today. Additional use cases with high potential include optimizing pricing, routing, and scheduling based on real-time data in travel and logistics; predicting personalized health outcomes, and optimizing merchandising strategy in retail. McKinsey identified 120 potential use cases of machine learning in 12 industries and surveyed more than 600 industry experts on their potential impact. They found an extraordinary breadth of potential applications for machine learning. Each of the use cases was identified as being one of the top three in an industry by at least one expert in that industry.


New Products

Science

Automation of isoelectric point measurement can be achieved using a BI-ZTU autotitrator in combination with a NanoBrook zeta potential analyzer, both from Testa Analytical Solutions. The stability of a dispersion is commonly determined by zeta potential. By studying the isoelectric point, scientists can evaluate how pH affects zeta potential and therefore can ascertain at which pH the zeta potential is zero. The BI-ZTU autotitrator option for NanoBrook zeta potential analyzers is ideal for automatic determination of the isoelectric point of colloids, for detection of the onset of aggregation as a function of pH, and for measuring the effect of salt concentration (ionic strength) on zeta potential. Using this setup allows you to determine zeta potential at a particular pH, then automatically repeat the measurement for the next pH in the series.