What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Her primary areas of study are Artificial intelligence, Machine learning, Bayesian network, Pattern recognition and Algorithm.
Her Artificial intelligence study frequently draws parallels with other fields, such as Cognitive load.
Her studies in Machine learning integrate themes in fields like Variety and Regression problems.
Her research in Bayesian network focuses on subjects like Inference, which are connected to Transaction processing, Distributed computing, Probabilistic logic and Information theory.
Her study in the fields of Convolutional neural network under the domain of Pattern recognition overlaps with other disciplines such as Invariant.
Her Algorithm study combines topics from a wide range of disciplines, such as Function, Key, Theoretical computer science and Resolution.
Her most cited work include:
- An empirical study of the naive Bayes classifier (1580 citations)
- Critical event prediction for proactive management in large-scale computer clusters (251 citations)
- Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks (233 citations)
What are the main themes of her work throughout her whole career to date?
Irina Rish focuses on Artificial intelligence, Machine learning, Pattern recognition, Data mining and Algorithm.
Her Artificial intelligence study focuses mostly on Reinforcement learning, Mutual information, Feature learning, Artificial neural network and Feature vector.
Irina Rish combines subjects such as Range and Parametric statistics with her study of Reinforcement learning.
Her Machine learning research includes themes of Variety, Neuroimaging and Forgetting.
Her Pattern recognition research incorporates themes from Voxel and Speedup.
The various areas that Irina Rish examines in her Bayesian network study include Probabilistic logic, Inference and Naive Bayes classifier.
She most often published in these fields:
- Artificial intelligence (49.75%)
- Machine learning (32.49%)
- Pattern recognition (13.71%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (49.75%)
- Machine learning (32.49%)
- Reinforcement learning (5.58%)
In recent papers she was focusing on the following fields of study:
Irina Rish mainly investigates Artificial intelligence, Machine learning, Reinforcement learning, Range and Process.
Irina Rish combines Artificial intelligence and Java hashCode in her studies.
She interconnects Variety and Forgetting in the investigation of issues within Machine learning.
Her research integrates issues of Management science and Reinforcement in her study of Reinforcement learning.
Her work carried out in the field of Artificial neural network brings together such families of science as Quality, Nonparametric statistics, Deep learning and Predictability.
To a larger extent, she studies Pattern recognition with the aim of understanding Mutual information.
Between 2018 and 2021, her most popular works were:
- A Survey on Practical Applications of Multi-Armed and Contextual Bandits. (37 citations)
- Beyond backprop: Online alternating minimization with auxiliary variables (21 citations)
- Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (19 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Her scientific interests lie mostly in Artificial intelligence, Machine learning, Reinforcement learning, Field and Adaptation.
Many of her studies on Artificial intelligence apply to Convergence as well.
Her research investigates the connection with Reinforcement learning and areas like Range which intersect with concerns in Neuropsychiatry.
Her Field research is multidisciplinary, relying on both Recommender system, Data science and Taxonomy.
Her Adaptation study integrates concerns from other disciplines, such as Forgetting, Continual learning and Process management.
Her multidisciplinary approach integrates Lifelong learning and Process in her work.
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.
