Variational Neural Cellular Automata
- URL: http://arxiv.org/abs/2201.12360v2
- Date: Wed, 2 Feb 2022 06:59:12 GMT
- Title: Variational Neural Cellular Automata
- Authors: Rasmus Berg Palm, Miguel Gonz\'alez-Duque, Shyam Sudhakaran, Sebastian
Risi
- Abstract summary: In nature, the process of cellular growth and differentiation has lead to an amazing diversity of organisms.
We propose a generative model, the Variational Cellular Automata (VNCA), which is loosely inspired by the biological processes of cellular growth and differentiation.
- Score: 7.863826008567604
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In nature, the process of cellular growth and differentiation has lead to an
amazing diversity of organisms -- algae, starfish, giant sequoia, tardigrades,
and orcas are all created by the same generative process. Inspired by the
incredible diversity of this biological generative process, we propose a
generative model, the Variational Neural Cellular Automata (VNCA), which is
loosely inspired by the biological processes of cellular growth and
differentiation. Unlike previous related works, the VNCA is a proper
probabilistic generative model, and we evaluate it according to best practices.
We find that the VNCA learns to reconstruct samples well and that despite its
relatively few parameters and simple local-only communication, the VNCA can
learn to generate a large variety of output from information encoded in a
common vector format. While there is a significant gap to the current
state-of-the-art in terms of generative modeling performance, we show that the
VNCA can learn a purely self-organizing generative process of data.
Additionally, we show that the VNCA can learn a distribution of stable
attractors that can recover from significant damage.
Related papers
- Generating Multi-Modal and Multi-Attribute Single-Cell Counts with CFGen [76.02070962797794]
We present Cell Flow for Generation, a flow-based conditional generative model for multi-modal single-cell counts.
Our results suggest improved recovery of crucial biological data characteristics while accounting for novel generative tasks.
arXiv Detail & Related papers (2024-07-16T14:05:03Z) - Meta-Learning an Evolvable Developmental Encoding [7.479827648985631]
Generative models have shown promise in being learnable representations for black-box optimisation.
Here we present a system that can meta-learn such representation by optimising for a representation's ability to generate quality-diversity.
In more detail, we show our meta-learning approach can find one Neural Cellular Automata, in which cells can attend to different parts of a "DNA" string genome during development.
arXiv Detail & Related papers (2024-06-13T11:52:06Z) - Unveiling the Unseen: Identifiable Clusters in Trained Depthwise
Convolutional Kernels [56.69755544814834]
Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures.
This paper reveals another striking property of DS-CNN architectures: discernible and explainable patterns emerge in their trained depthwise convolutional kernels in all layers.
arXiv Detail & Related papers (2024-01-25T19:05:53Z) - Neural Echos: Depthwise Convolutional Filters Replicate Biological
Receptive Fields [56.69755544814834]
We present evidence suggesting that depthwise convolutional kernels are effectively replicating the biological receptive fields observed in the mammalian retina.
We propose a scheme that draws inspiration from the biological receptive fields.
arXiv Detail & Related papers (2024-01-18T18:06:22Z) - Modelling Technical and Biological Effects in scRNA-seq data with
Scalable GPLVMs [6.708052194104378]
We extend a popular approach for probabilistic non-linear dimensionality reduction, the Gaussian process latent variable model, to scale to massive single-cell datasets.
The key idea is to use an augmented kernel which preserves the factorisability of the lower bound allowing for fast variational inference.
arXiv Detail & Related papers (2022-09-14T15:25:15Z) - Growing Isotropic Neural Cellular Automata [63.91346650159648]
We argue that the original Growing NCA model has an important limitation: anisotropy of the learned update rule.
We demonstrate that cell systems can be trained to grow accurate asymmetrical patterns through either of two methods.
arXiv Detail & Related papers (2022-05-03T11:34:22Z) - Modeling Protein Using Large-scale Pretrain Language Model [12.568452480689578]
Interdisciplinary researchers have begun to leverage deep learning methods to model large biological datasets.
Inspired by the similarity between natural language and protein sequences, we use large-scale language models to model evolutionary-scale protein sequences.
Our model can accurately capture evolution information from pretraining on evolutionary-scale individual sequences.
arXiv Detail & Related papers (2021-08-17T04:13:11Z) - Towards an Automatic Analysis of CHO-K1 Suspension Growth in
Microfluidic Single-cell Cultivation [63.94623495501023]
We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data.
Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
arXiv Detail & Related papers (2020-10-20T08:36:51Z) - Predicting Geographic Information with Neural Cellular Automata [7.605218364952221]
This paper presents a novel framework using neural cellular automata (NCA) to regenerate and predict geographic information.
The model extends the idea of using NCA to generate/regenerate a specific image by training the model with various geographic data.
arXiv Detail & Related papers (2020-09-20T03:53:48Z) - Neural Cellular Automata Manifold [84.08170531451006]
We show that the neural network architecture of the Neural Cellular Automata can be encapsulated in a larger NN.
This allows us to propose a new model that encodes a manifold of NCA, each of them capable of generating a distinct image.
In biological terms, our approach would play the role of the transcription factors, modulating the mapping of genes into specific proteins that drive cellular differentiation.
arXiv Detail & Related papers (2020-06-22T11:41:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.