What is she best known for?
The fields of study Daphna Weinshall is best known for:
- Statistics
- Machine learning
- Geometry
In her study, Projection (relational algebra) is inextricably linked to Algorithm, which falls within the broad field of Computational complexity theory.
Her study connects Class (philosophy) and Artificial intelligence.
As part of her studies on Pattern recognition (psychology), she often connects relevant subjects like Artificial intelligence.
Her Computer vision study frequently links to related topics such as Silhouette.
Her Image (mathematics) study frequently links to related topics such as Contextual image classification.
Her Contextual image classification study frequently links to other fields, such as Image (mathematics).
In her articles, she combines various disciplines, including Neuroscience and Perception.
Perception is often connected to Stimulus generalization in her work.
Daphna Weinshall regularly links together related areas like Neuroscience in her Stimulus generalization studies.
Her most cited work include:
- Flexible syntactic matching of curves and its application to automatic hierarchical classification of silhouettes (227 citations)
- Learning a Mahalanobis Metric from Equivalence Constraints (211 citations)
- Classification with nonmetric distances: image retrieval and class representation (205 citations)
What are the main themes of her work throughout her whole career to date
Her Artificial intelligence research is intertwined with Pattern recognition (psychology), Image (mathematics), Object (grammar) and Motion (physics).
Many of her studies involve connections with topics such as Image (mathematics) and Computer vision.
She integrates many fields, such as Algorithm and Computer vision, in her works.
In her research, Daphna Weinshall performs multidisciplinary study on Geometry and Point (geometry).
In her work, Daphna Weinshall performs multidisciplinary research in Point (geometry) and Geometry.
She conducts interdisciplinary study in the fields of Machine learning and Artificial intelligence through her works.
Her study deals with a combination of Law and Politics.
She performs integrative Politics and Representation (politics) research in her work.
Her Representation (politics) study frequently draws connections to other fields, such as Law.
Daphna Weinshall most often published in these fields:
- Artificial intelligence (82.46%)
- Computer vision (45.61%)
- Pattern recognition (psychology) (35.09%)
What were the highlights of her more recent work (between 2015-2020)?
- Machine learning (83.33%)
- Artificial intelligence (83.33%)
- Pedagogy (50.00%)
In recent works Daphna Weinshall was focusing on the following fields of study:
Her Mathematical analysis study frequently intersects with other fields, such as Generalization and Monotonic function.
Her research ties Mathematical analysis and Generalization together.
Her Mathematical optimization research is intertwined with Heuristics and Empirical risk minimization.
Her study in Mathematical optimization extends to Heuristics with its themes.
Daphna Weinshall performs multidisciplinary study on Empirical risk minimization and Support vector machine in her works.
Part of her project on Support vector machine includes research on Hinge loss and Binary classification.
She is involved in relevant fields of research such as Ideal (ethics) and Simple (philosophy) in the field of Epistemology.
Her work in Simple (philosophy) is not limited to one particular discipline; it also encompasses Epistemology.
Regular polygon and Ideal point are all intertwined in Geometry research.
Between 2015 and 2020, her most popular works were:
- Distance-based Confidence Score for Neural Network Classifiers (32 citations)
- Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images. (19 citations)
- On The Power of Curriculum Learning in Training Deep Networks (16 citations)
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
