Our method is evaluated on an own experiment and over 50.000 number series from the Online Encyclopedia of Integer Sequences (OEIS) database.Marco RagniAndreas KleinKI 2010: Advances in Artificial Intelligence: 34th Annual German Conference on AI, Berlin, Germany, October 4-7, 2011, Proceedings...
Here, we present a deep learning model (DLM) for predicting Next-Generation Sequencing (NGS) depth from DNA probe sequences. Our DLM includes a bidirectional recurrent neural network that takes as input both DNA nucleotide identities as well as the calculated probability of the nucleotide being ...
Using analytical and numerical methods, estimates are given of future predictions in astrophysics that can be gathered from a sequence of observed events, for example for 纬-ray bursts. Some general probability considerations are provided and then a maximum likelihood estimation, together with an ...
a protein’s biological function often depends on multiple conformational substates2, and disease-causing point mutations often cause population changes within these substates3,4. We demonstrate that clustering a multiple-sequence alignment by sequence similarity enables AlphaFold...
(2)Em,u[1T∑t=0T‖Rˆ(fˆ0:t,u0:t,m)−R(f0:t,u0:t,m)‖22]→minRˆ,where the sequence of approximated reservoir states fˆ0:t is obtained from the approximated transition function Fˆ, and the initial states are computed as follows:(3)f0=Finit(m),fˆ0=Fˆinit...
Next, we sought to estimate the maximum possible performance for predicting gene expression from promoter sequences alone. A genome-wide MPRA measuring autonomous promoter activity in K562 cells, called Survey of Regulatory Elements (SuRE), linked 200 bp to 2-kb regions of the genome to an episo...
Neil D, Pfeiffer M, Liu SC (2016) Phased LSTM: accelerating recurrent network training for long or event-based sequences. In: Advances in neural information processing systems, pp 3882–3890 Lavin A, Gray S (2016) Fast algorithms for convolutional neural networks. In: Proceedings of the IEEE...
This rule is rooted in the obvious trendin computing costs: all forms of hardware are becoming cheaper, even as they become faster and more reliable. Whether Moore’s Law (Gordon E. Moore’s now-famous axiom in 1965 that postulates that the number of transistors on an integrated circuit app...
A type of model generalization known as transfer learning14,15 is one potential solution to overcome the problem of data sparsity. Generalizing ML models using transfer learning has been applied in a number of areas in geophysics; for instance in seismology applications, transfer learning has been ...
on the data. When predicting the congestion, more accurate results can be obtained with the SARIMA. According to the prediction consequences in the SARIMA model, the unit node ratio sequence of the period and trend information is extracted, and the results are revised34. The process can be ...