What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Paolo Frasconi focuses on Artificial intelligence, Machine learning, Artificial neural network, Recurrent neural network and Supervised learning.
His Artificial intelligence research incorporates elements of Theoretical computer science and Pattern recognition.
The various areas that Paolo Frasconi examines in his Machine learning study include Amino acid, Numerical analysis, Face and Gradient method.
His Artificial neural network research is multidisciplinary, incorporating elements of Function and Pattern recognition.
His studies in Recurrent neural network integrate themes in fields like Gradient descent, Algorithm, Leverage and Protein secondary structure prediction.
His Supervised learning research is multidisciplinary, relying on both Graphical model, Data mining and Time series.
His most cited work include:
- Learning long-term dependencies with gradient descent is difficult (4086 citations)
- Exploiting the past and the future in protein secondary structure prediction. (410 citations)
- A general framework for adaptive processing of data structures (402 citations)
What are the main themes of his work throughout his whole career to date?
Paolo Frasconi mainly investigates Artificial intelligence, Machine learning, Artificial neural network, Theoretical computer science and Recurrent neural network.
His Artificial intelligence study incorporates themes from Statistical relational learning, Pattern recognition and Natural language processing.
Paolo Frasconi combines subjects such as Protein secondary structure and Hidden Markov model with his study of Machine learning.
His biological study focuses on Gradient descent.
His Theoretical computer science research includes elements of Graph, Aggregate, Kernel method and Graph.
Paolo Frasconi interconnects Connectionism and Feedforward neural network in the investigation of issues within Recurrent neural network.
He most often published in these fields:
- Artificial intelligence (61.96%)
- Machine learning (29.35%)
- Artificial neural network (23.37%)
What were the highlights of his more recent work (between 2014-2021)?
- Artificial intelligence (61.96%)
- Deep learning (9.78%)
- Theoretical computer science (20.65%)
In recent papers he was focusing on the following fields of study:
Paolo Frasconi mostly deals with Artificial intelligence, Deep learning, Theoretical computer science, Hyperparameter optimization and Artificial neural network.
The Artificial intelligence study combines topics in areas such as Machine learning and Computer vision.
His work carried out in the field of Machine learning brings together such families of science as Knowledge extraction and Data science.
The various areas that Paolo Frasconi examines in his Theoretical computer science study include Graph, Graph kernel and Graph.
His Hyperparameter optimization study also includes fields such as
- Mathematical optimization which intersects with area such as Meta learning,
- Speedup, Task, Stochastic gradient descent and Recurrent neural network most often made with reference to Hyperparameter,
- Algorithm which is related to area like Embedding, Interpolation and Generator.
His research in Artificial neural network focuses on subjects like Aggregate, which are connected to Boolean function, Contextual image classification, Class and Kernel method.
Between 2014 and 2021, his most popular works were:
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning (125 citations)
- Forward and Reverse Gradient-Based Hyperparameter Optimization (88 citations)
- Whole-Brain Vasculature Reconstruction at the Single Capillary Level. (53 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
His scientific interests lie mostly in Hyperparameter, Hyperparameter optimization, Supervised learning, Mathematical optimization and Artificial intelligence.
His work deals with themes such as Recurrent neural network, Stochastic gradient descent, Speedup and Task, which intersect with Hyperparameter.
His research integrates issues of Gradient based algorithm and Algorithm in his study of Recurrent neural network.
The study incorporates disciplines such as Optimization problem, Bilevel optimization, Representation, Set and Meta learning in addition to Supervised learning.
His research on Artificial intelligence frequently connects to adjacent areas such as Boolean function.
His research in Deep learning intersects with topics in Artificial neural network, Theoretical computer science and Aggregate.
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.
