Welcome to the Sensorium 2023 Competition!

The Sensorium 2023 competition is over. Here are the winning teams:
All winners used custom architectures. To learn more about their approaches, join our in-person workshop at NeurIPS on Friday, Dec 15, 2023. ūüóďÔłŹ


The Problem

Even today’s most advanced models of visual cortex are not able to fully predict the brain’s responses.

Understanding how the brain processes visual input is a long standing goal in neuroscience. To solve this question in a quantitative, testable, and reproducible way, accurate predictive models of neural population responses to natural stimuli are crucial. However, even today’s most advanced models of visual cortex are only able to account for a fraction of the observed neuronal activity. Furthermore, because there is an abundance of models and metrics, but no widely-used reference dataset, it is challenging to compare models on equal ground. This makes it difficult to determine the current state-of-the-art model.

SENSORIUM 2023 schematic

The SENSORIUM 2023 Competition

Benchmarking the predictive performance of your model on large-scale datasets.

The SENSORIUM 2023 competition offers a publicly available, large-scale dataset consisting of the activity from over 38,000 neurons from the primary visual cortex of five different mice in response to around 1800 natural scene videos (around 10 seconds). The dataset also includes additional behavioral measurements such as running speed, pupil dilation and eye movements. The performance of predictive models can be automatically evaluated by submitting predicted neural responses to our website which will display the performance of all submissions in a leaderboard for easy comparison.

The SENSORIUM 2022 competition approached this issue for static stimulus (pictures) models. This year we are adding a time dimensional component and try to inspire community to establish a benchmark dataset and a model for dynamic stimulus (videos). See more about data in the whitepaper and data section.

Currently, we offer two benchmark tracks

There is a main track and a bonus track. The focus of the main track is to predict the neuronal activity for dynamic stimuli, while the focus of the bonus is to generalize to out of domain (OOD) stimuli.

Main Track

We provide data from 5 mice, more than 38,000 neurons, around 1800 natural scene videos (around 10 seconds), and additionally behavioral activity (pupil center, pupil dilation, and running speed). The goal is to train a networks, which would predict the neuronal activity for the neurons. To see more details about data or metrics see the corresponding section. Please note that this year there is not separate track for behaviour. It is up for the team if they want to use behavioural data or not.

Bonus Track

We think that from a biological perspective it is crucial to have not only good performing but also generalizable models. Hence, we establish a bonus track with five out of domain (OOD) stimuli to measure the models’ generalizable capabilities. This track would have one winning team.

Let’s predict how the brain processes what we see!


Getting Started

To ensure you have a swift and easy start participating in our competition we prepared a starting kit for you. The starting kit (link to Github https://github.com/ecker-lab/sensorium_2023) includes a comprehensive 3-step manual with code examples for installing required software, downloading and inspecting the competition data, and training and submitting a model to the competition website.


Call for Posters

We would like to invite you to submit a poster for our NeurIPS 2023 ‚ÄúSensorium‚ÄĚ competition workshop on December 15th! We are very interested to talk to everyone from the machine learning and computational neuroscience communities and discuss how to improve brain modelling. The topics include (but not limited to):

To present a poster, please submit an abstract (max. 250 words, plus names and afiliations) to sensorium.codalab@gmail.com as pdf before Nov 23, 23:59, Anywhere on Earth. Abstracts will be reviewed by workshop organizers for topic relevancy.


2023-11-02 NeurIPS workshop

We are happy to announce that we are hosting an in-person workshop at NeurIPS on Friday, Dec 15, 2023!
The workshop includes three keynote speakers and a poster session. Meet our brilliant keynotes speakers:

See Call for Posters above for more information on how to participate in the poster session!

2023-09-15 Submission deadline extension

We decided to extend the competition deadline to Oct. 15. This gives everyone another full month to improve their models or develop new approaches. Happy coding!

2023-09-15 Problems

We’ve recently discovered a few issues with the competition code, which we want to communicate for transparency:

  1. The official data loader uses non-standard normalization for neuronal responses. Since the evaluation code also uses this data loader, please use the official data loader in your code for consistency (details below).
  2. The evaluation of the avg. trial correlation metric was not computed correctly on the CodaLab competition page. We have updated the evaluation script and will re-evaluate your submissions. There is no action necessary by you.
  3. The bonus track submission system was broken due to file size restrictions. The workaround is to upload the prediction for the live and final test sets separately. We have updated the documentation to reflect this.

Details on normalization: We recently discovered a minor bug in our data export code that causes the neuronal response to be normalized per video frame instead of by one single number for each neuron when using the officially provided data loader. Since the evaluation code also uses that data loader, the code ‚Äď albeit using a non-standard normalization ‚Äď is self-consistent. However, if you are using a custom data loader, it might result in unexpected results. Thus we recommend using the official data loader.

We tested how much prediction results are affected by using the non-standard normalization compared to when normalizing neurons by a single number and found the differences to be minor. Therefore we decided to not change anything for now and conclude the competition with this non-standard normalization. We apologize for any inconvenience this might have caused.

2023-07-21 New dataset

Dear participants,
as promised, we have updated the dataset - you can access the new dataset here - https://gin.g-node.org/pollytur/sensorium_2023_dataset.
The previous dataset stays online and you can use it for the competition as well. We added a new competition to codalab: Sensorium 2023 - Main Track [new].

2023-06-22 Data release

Unfortunately our data release for the Sensorium 2023 competition accidentally included the secret test set. Although we took the file offline immediately after finding out about it, it is not clear how many people gained access to the dataset. We therefore consider it compromised. To ensure a fair continuation of the competition, we will take the following actions:

  1. We are in the process of collecting a new dataset that will replace the original one.
  2. The current competition on CodaLab will be kept open for development purposes only. We will create a new instance with the new secret test set that will be used to determine the winners of the competition. Any models submitted on the current CodaLab competition will have to be resubmitted on the new one.
  3. Once the new dataset and competition are available, we will make another public announcement to inform all participants about the procedures.

We would like to apologize to all participants for the extra work and hassle this may cause. Thank you to Kaiwen Deng for immediately reporting this issue to us!


Q: What is this competition about?
We are looking for the best neural predictive model that can predict the activity of thousands of neurons in the primary visual cortex of mice in response to videos.

Q: Why are neural predictive models interesting?
Accurate models of neuronal activity can serve as phenomenological digital twins for the visual cortex, allowing computational neuroscientists to derive new hypotheses about biological vision ‚Äúin silico‚ÄĚ, enabling systems neuroscientists to test them ‚Äúin vivo‚ÄĚ. On top of that, these models are relevant to machine learning researchers who use them to bridge the gap between biological and machine vision.

Q: Where will the results be presented?
We are happy to announce that we are part of the NeurIPS 2023 competition track! We’ll host a workshop at NeurIPS in December 2023 to present the winners and overall results of this competition.

Q: Are there plans for future data and competition releases?
We intend to start the competition this year at NeurIPS, but keep the website open for new challenges to make this website a valuable resource for data driven neural system identification models in mouse visual cortex and beyond.


Polina Turishcheva (University of Göttingen) Eric Y. Wang (Baylor College of Medicine)
Konstantin F. Willeke (University of T√ľbingen) Paul G. Fahey (Baylor College of Medicine)
Laura Hansel (University of G√∂ttingen) Michaela Vystrńćilov√° (University of G√∂ttingen)
Mohammad Bashiri (University of T√ľbingen) Zhiwei Ding (Baylor College of Medicine)
Kayla Ponder (Baylor College of Medicine) Alexander Ecker (University of Göttingen)
Andreas S. Tolias (Baylor College of Medicine) Fabian H. Sinz (University of Göttingen)


Have more questions? Join our slack workspace! Or contact us at contact@sensorium-competition.net.