What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Sanjiv Kumar mainly focuses on Artificial intelligence, Pattern recognition, Mathematical optimization, Locality-sensitive hashing and Feature hashing.
His work deals with themes such as Hash function and Computer vision, which intersect with Artificial intelligence.
His Pattern recognition research includes themes of Contextual image classification, Object detection, Graph and Image retrieval.
His Mathematical optimization study combines topics in areas such as Algorithm, Rounding and Exponential function.
Sanjiv Kumar interconnects Universal hashing and Dynamic perfect hashing in the investigation of issues within Locality-sensitive hashing.
He has researched Hopscotch hashing in several fields, including Theoretical computer science, 2-choice hashing, Open addressing, Nearest neighbor search and K-independent hashing.
His most cited work include:
- On the Convergence of Adam and Beyond (857 citations)
- Hashing with Graphs (848 citations)
- Semi-Supervised Hashing for Large-Scale Search (601 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Pattern recognition, Algorithm, Machine learning and Embedding.
His work on Computer vision expands to the thematically related Artificial intelligence.
K-nearest neighbors algorithm is closely connected to Hash function in his research, which is encompassed under the umbrella topic of Pattern recognition.
He focuses mostly in the field of Algorithm, narrowing it down to matters related to Mathematical optimization and, in some cases, Exponential function.
Sanjiv Kumar has included themes like Contextual image classification and Training set in his Machine learning study.
His research on Embedding also deals with topics like
- Time complexity that connect with fields like Binary number,
- Binary code which intersects with area such as Curse of dimensionality.
He most often published in these fields:
- Artificial intelligence (53.33%)
- Pattern recognition (22.38%)
- Algorithm (20.48%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (53.33%)
- Machine learning (18.10%)
- Transformer (4.29%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Machine learning, Transformer, Embedding and Pattern recognition.
His research on Artificial intelligence often connects related areas such as Convergence.
His studies in Machine learning integrate themes in fields like Training set and Federated learning.
His Transformer study incorporates themes from Theoretical computer science, Information retrieval and Computer engineering.
The various areas that Sanjiv Kumar examines in his Embedding study include Classifier and Feature learning.
His Pattern recognition study integrates concerns from other disciplines, such as Smoothing and Logit.
Between 2019 and 2021, his most popular works were:
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (133 citations)
- Adaptive Federated Optimization (69 citations)
- Pre-training Tasks for Embedding-based Large-scale Retrieval (52 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Transformer, Convergence and Deep learning.
His Artificial intelligence study frequently draws connections between adjacent fields such as Simple.
His Machine learning research incorporates themes from Simple and Training set.
His Transformer research includes elements of Self attention, Embedding and Information retrieval.
His biological study spans a wide range of topics, including Key and Clipping.
His work carried out in the field of Deep learning brings together such families of science as Smoothing, Stochastic gradient descent, Stochastic optimization and Hyperparameter.
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.
