Alexander Lerchner

5.3k citations

15 papers · 1.4k indexed · 1 hit paper · h-index 8

Impact in

Computer Vision and Pattern Recognition top 2%
- Generative Adversarial Networks and Image Synthesis
- Multimodal Machine Learning Applications
Artificial Intelligence top 2%
- Domain Adaptation and Few-Shot Learning
- Topic Modeling
- Anomaly Detection Techniques and Applications
- Adversarial Robustness in Machine Learning

Papers in

Statistical and Nonlinear Physics 4
- stochastic dynamics and bifurcation 4
Cognitive Neuroscience 6
- Neural dynamics and brain function 6
- Visual perception and processing mechanisms 2

Co-authors: Löıc Matthey Christopher Burgess Irina Higgins Matthew Botvinick Arka Pal Xavier Glorot Shakir Mohamed John Hertz
Journals: Neurocomputing (3 papers)Neural Computation (2 papers)Network Computation in Neural Systems (1 paper)UCL Discovery (University College London) (1 paper)arXiv (Cornell University) (3 papers)
Partner nations: United States United Kingdom Denmark

In The Last Decade

Alexander Lerchner

15 papers receiving 1.3k citations

Hit Papers

align trajectories log scale

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework 2017 · 1.2k citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2017 International Conference on Learning Representations

Peers

Countries citing papers authored by Alexander Lerchner

Since Specialization

Citations

This map shows the geographic impact of Alexander Lerchner's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Alexander Lerchner with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Alexander Lerchner more than expected).

Fields of papers citing papers by Alexander Lerchner

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Alexander Lerchner. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Alexander Lerchner. The network helps show where Alexander Lerchner may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Alexander Lerchner, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Alexander Lerchner Line = papers co-authored together Alexander Lerchner links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

15 of 15 papers shown

#	Work
1	SODA: Bottleneck Diffusion Models for Representation Learning Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K. Lampinen, Andrew Jaegle, James L. McClelland, Löıc Matthey, Felix Hill, Alexander Lerchner	2024	5
2	PARTS: Unsupervised segmentation with slots, attention and independence maximization 2021 IEEE/CVF International Conference on Computer Vision (ICCV) ·Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo Jimenez Rezende	2021	7
3	Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents arXiv (Cornell University) ·Jane X. Wang, Michael C. King, Baker Qanita Bani, Zeb Kurth‐Nelson, Gustavo Omar Benvenuto, Jérémie Berdugo, Jürgen Spitzmüller, 竹夫成毛, Malcolm Reynolds, Hao Song, B.J. Green, David Reichert, Neil C. Rabinowitz, Löıc Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick	2021	4
4	Unsupervised Model Selection for Variational Disentangled Representation Learning International Conference on Learning Representations ·G. M. Minesinger, Löıc Matthey, André Saraiva, 黄星宇, Chris Burgess, Alexander Lerchner, Irina Higgins	2020	5
5	A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning. arXiv (Cornell University) ·G. M. Minesinger, Nicholas Watters, Löıc Matthey, Christopher Burgess, Alexander Lerchner, Irina Higgins	2019	1
6	Multi-Object Representation Learning with Iterative Variational Inference arXiv (Cornell University) ·Klaus Greff, Dongjiang Han, Rishabh Kabra, 黄星宇, Christopher Burgess, Daniel Zoran, Löıc Matthey, Matthew Botvinick, Alexander Lerchner	2019	13
7	SCAN: Learning Hierarchical Compositional Visual Concepts UCL Discovery (University College London) ·Irina Higgins, Nicolas Sonnerat, Löıc Matthey, Arka Pal, Christopher Burgess, Matko Bošnjak, Murray Shanahan, Matthew Botvinick, Demis Hassabis, Alexander Lerchner	2018	17
8	Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies Neural Information Processing Systems ·Alessandro Achille, Tom Eccles, Löıc Matthey, Christopher Burgess, Nicholas Watters, Alexander Lerchner, Irina Higgins	2018	18
9	beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework International Conference on Learning Representations ·Irina Higgins, Löıc Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner Hit paper breakdown →	2017	1198
10	Response Variability in Balanced Cortical Networks Neural Computation ·Alexander Lerchner, Dang-Thi NT, John Hertz, Nóra Bakos-Barczi, A. Sticht, Abdelkader El Khider	2006	21
11	Response Variability in Balanced Cortical Networks Neural Computation ·Alexander Lerchner, Dang-Thi NT, John Hertz, Nóra Bakos-Barczi, A. Sticht, Abdelkader El Khider	2006	34
12	Mean field theory for a balanced hypercolumn model of orientation selectivity in primary visual cortex Network Computation in Neural Systems ·Alexander Lerchner, Sana' Rajab, John Hertz, Nóra Bakos-Barczi	2006	21
13	Synaptic model for spontaneous activity in developing networks Neurocomputing ·Alexander Lerchner, John Rinzel	2004	1
14	High-conductance states in a mean-field cortical network model Neurocomputing ·Alexander Lerchner, Nóra Bakos-Barczi, John Hertz	2004	15
15	High-conductance states in a mean-field cortical network model Neurocomputing ·Alexander Lerchner	2004	1

About Alexander Lerchner

Alexander Lerchner is a scholar working on Statistical and Nonlinear Physics, Cognitive Neuroscience, Artificial Intelligence, Computer Vision and Pattern Recognition and Biophysics, having authored 15 papers that have together received 1.4k indexed citations. Recurring topics across this work include Neural dynamics and brain function (6 papers), stochastic dynamics and bifurcation (4 papers), Domain Adaptation and Few-Shot Learning (4 papers), Generative Adversarial Networks and Image Synthesis (3 papers), Photoreceptor and optogenetics research (2 papers), Visual perception and processing mechanisms (2 papers), Advanced Image and Video Retrieval Techniques (2 papers) and Machine Learning and Data Classification (2 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (616 citations), Artificial Intelligence (711 citations), Signal Processing (144 citations), Statistical and Nonlinear Physics (107 citations) and Cognitive Neuroscience (160 citations). Alexander Lerchner has collaborated with scholars based in United States, United Kingdom and Denmark. Frequent co-authors include Löıc Matthey, Christopher Burgess, Irina Higgins, Matthew Botvinick, Arka Pal, Xavier Glorot, Shakir Mohamed, John Hertz, Daniel Zoran and Tom Eccles. Their work appears in journals such as Neurocomputing, Neural Computation, Network Computation in Neural Systems, UCL Discovery (University College London) and arXiv (Cornell University).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact