Abstract: The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning models using biological systems (e.g. brain data) to engineer machine-learning-algorithms that can generalize better. Particularly, aspects are directed to a computer implemented method that includes measuring a plurality of biological responses (e.g. neural responses to stimuli or other variables such body movements); generating data (e.g. responses to stimuli) using the predictive model which can denoise biological data and extract task relevant information; scaling and transforming these predictions (e.g. measure representational similarities between stimuli); and using the biologically derived data to regularize machine-learning-algorithms.
Type:
Application
Filed:
September 24, 2020
Publication date:
September 8, 2022
Applicants:
BAYLOR COLLEGE OF MEDICINE, UNIVERSITY OF TUBINGEN
Inventors:
ANDREAS TOLIAS, ZHE LI, ZACHARY PITKOW, JOSUE ORTEGA CARO, ANKIT PATEL, JACOB REIMER, MATTHIAS BETHGE, FABIAN SINZ
Abstract: A dielectrophoretic fractionation device having a channel defining a direction of flow therethrough for the fractionation of particles in a liquid particle suspension is disclosed. The device also has a deflector unit affixed to a wall of the channel and arranged to generate an electric field gradient in the channel to spatially separate the particles in the liquid particle suspension. The device also has an actuator mounted to the channel and positioned to deform the wall. Also provided is a method for inhibiting aggregation of particles in a liquid particle suspension of the dielectrophoretic fractionation device, the method including periodically deforming the wall with the actuator.
Type:
Application
Filed:
January 30, 2009
Publication date:
February 9, 2012
Applicants:
Natural and Medical Sciences Institute at the University of Tubingen, Bio-Rad Laboratories, Inc.
Inventors:
Monika Hausmann, Meike Moschallski, Anton Posch, Martin Stelzle, Joerg Kentsch, Simon Werner
Abstract: The present invention is relative to nucleic acids containing at least one nucleic acid sequence coding for a recombinant polypeptide, which recombinant polypeptide contains at least partially the primary sequence of the invariant chain and at least one primary sequence from a specific T-cell epitope and is processed in a desired manner in antigen-presenting cells for binding the specific T-cell epitope to MHC II molecules.