Events

We will discuss about "Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization", Wang, Yingfan, et al., J. Mach. Learn. Res., 2021. Abstract: Dimension reduction (DR) techniques such as t-SNE, UMAP, and TriMAP have demonstrated impressive visualization performance on many real world datasets. One tension …

We will discuss about "AI Pontryagin or how artificial neural networks learn to control dynamical systems", Böttcher, L., Antulov-Fantulin, N. & Asikis, T., Nat Commun 13, 333 (2022). Abstract: The efficient control of complex dynamical systems has many applications in the natural and applied sciences. In most real-world control problems, both control energy and cost …

We will discuss about "Chemical Organisation Theory ", Dittrich, Peter, and Pietro Speroni Di Fenizio, Bulletin of mathematical biology 69.4 (2007): 1199-1231. Abstract: Complex dynamical reaction networks consisting of many components that interact and produce each other are difficult to understand, especially, when new component types may appear and present component types may vanish completely. …

We will discuss about "Accuracy and limitations of extrinsic noise models to describe gene expression in growing cells", Jia, Chen, and Ramon Grima, bioRxiv (2022). Abstract: The standard model describing the fluctuations of mRNA numbers in single cells is the telegraph model which includes synthesis and degradation of mRNA, and switching of the gene between …

We will discuss about "Learning stable and predictive structures in kinetic systems", Niklas Pfister , Stefan Bauer, and Jonas Peters. PNAS, 2019 Abstract: Learning kinetic systems from data is one of the core challenges in many fields. Identifying stable models is essential for the generalization capabilities of data-driven inference. We introduce a computationally efficient framework, …

We will discuss about "Neural Ordinary Differential Equations", Chen, Ricky TQ, et al., Advances in neural information processing systems 31 (2018). Abstract: We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output …

We will discuss about "Molecular convolutional neural networks with DNA regulatory circuits", Pei, Hao, et al., Nature Machine Intelligence (2022): 1-11. Abstract: Complex biomolecular circuits enabled cells with intelligent behaviour to survive before neural brains evolved. Since DNA computing was first demonstrated in the mid-1990s, synthetic DNA circuits in liquid phase have been developed as …