What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
The scientist’s investigation covers issues in Artificial neural network, Algorithm, Artificial intelligence, Mars Exploration Program and Function.
His work carried out in the field of Artificial neural network brings together such families of science as Variation, Data parallelism and Computer engineering.
His Algorithm study combines topics in areas such as Covariance function, Jacobian matrix and determinant, Convolutional neural network and Contextual image classification.
His Artificial intelligence research is multidisciplinary, incorporating elements of Machine learning and Computation.
His Machine learning study combines topics from a wide range of disciplines, such as Sampling, Probabilistic logic, Density estimation and Inference.
He interconnects Pixel, Optics and Remote sensing in the investigation of issues within Mars Exploration Program.
His most cited work include:
- Density estimation using Real NVP (704 citations)
- Stratigraphy and sedimentology of a dry to wet eolian depositional system, Burns formation, Meridiani Planum, Mars (414 citations)
- Unrolled Generative Adversarial Networks (385 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Artificial neural network, Algorithm, Machine learning and Gaussian process.
His Artificial intelligence study frequently links to adjacent areas such as Pattern recognition.
The Artificial neural network study combines topics in areas such as Regularization, Kernel and Task.
The concepts of his Algorithm study are interwoven with issues in Subspace topology, Stochastic gradient descent, Markov chain Monte Carlo, Jacobian matrix and determinant and Function.
His work in the fields of Unsupervised learning and Convolutional neural network overlaps with other areas such as Process.
Jascha Sohl-Dickstein has included themes like Sampling, Probabilistic logic, Inference and Generative model in his Unsupervised learning study.
He most often published in these fields:
- Artificial intelligence (36.94%)
- Artificial neural network (33.12%)
- Algorithm (29.30%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial neural network (33.12%)
- Algorithm (29.30%)
- Artificial intelligence (36.94%)
In recent papers he was focusing on the following fields of study:
Jascha Sohl-Dickstein spends much of his time researching Artificial neural network, Algorithm, Artificial intelligence, Gaussian process and Machine learning.
His study in the field of Gradient descent is also linked to topics like Kernel.
His Algorithm research incorporates elements of Sampling and Markov chain Monte Carlo.
When carried out as part of a general Artificial intelligence research project, his work on Deep learning, Backpropagation and Recurrent neural network is frequently linked to work in Meta learning, therefore connecting diverse disciplines of study.
He focuses mostly in the field of Deep learning, narrowing it down to topics relating to Statistical physics and, in certain cases, Linear model.
The various areas that Jascha Sohl-Dickstein examines in his Machine learning study include Contextual image classification and Optimization problem.
Between 2018 and 2021, his most popular works were:
- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent (273 citations)
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (129 citations)
- Statistical Mechanics of Deep Learning (44 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His scientific interests lie mostly in Artificial neural network, Algorithm, Gaussian process, Deep learning and Artificial intelligence.
Jascha Sohl-Dickstein is interested in Gradient descent, which is a field of Artificial neural network.
His Algorithm study incorporates themes from Laplace transform, Activation function, Feedforward neural network and Nonlinear system.
His study with Deep learning involves better knowledge in Machine learning.
His research in Machine learning focuses on subjects like Norm, which are connected to Backpropagation.
His work often combines Artificial intelligence and Jamming studies.
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.
