NeuronStarhttps://neuronstar.github.io/Recent content on NeuronStarHugo -- gohugo.ioen-USThu, 24 Mar 2016 00:00:00 +0000Conditional Probability and Bayeshttps://neuronstar.github.io/cpe/01.conditional-probability-and-bayes/Wed, 18 Nov 2020 00:00:00 +0000https://neuronstar.github.io/cpe/01.conditional-probability-and-bayes/The Bayesian view of probability is quite objective and also more general than the frequentist’s view. It doesn’t rely on repeatition of events.01.Neuron Biological Propertieshttps://neuronstar.github.io/snm/01.single_neuron_model/Fri, 18 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/01.single_neuron_model/Neuron biological propertiesLeast Squares, Bootstrap, Maximum Likelihood, and Bayesianhttps://neuronstar.github.io/cpe/02.least-squares-bootstrap-maximum-likelihood-and-bayesian/Sat, 12 Dec 2020 00:00:00 +0000https://neuronstar.github.io/cpe/02.least-squares-bootstrap-maximum-likelihood-and-bayesian/Least squares, bootstrap, maximum likelihood, and maximum posterior leads to the same results in many cases.02.Review of Last Week's Readinghttps://neuronstar.github.io/snm/02.limitations_srm_contd_and_coding/Fri, 18 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/02.limitations_srm_contd_and_coding/Review of Last Week’s ReadingEM Methodshttps://neuronstar.github.io/cpe/03.em-methods/Sat, 02 Jan 2021 00:00:00 +0000https://neuronstar.github.io/cpe/03.em-methods/Topics EM for Gaussian mixtures General EM algorithm Why does it work? Decomposition of log-likelihood into KL divergence and Relation between EM and Gibbs sampling03.Equilibrium Potential and Hodgkin-Huxley Modelhttps://neuronstar.github.io/snm/03.equilibrium_potential_and_hodgkin-huxley_model/Sun, 13 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/03.equilibrium_potential_and_hodgkin-huxley_model/Equilibrium Potential and Hodgkin-Huxley ModelVariantional Inference Normalizing Flowhttps://neuronstar.github.io/cpe/04.variational-inference-normalizing-flow/Sat, 16 Jan 2021 00:00:00 +0000https://neuronstar.github.io/cpe/04.variational-inference-normalizing-flow/Topics Variational Inference Normalizing Flow Variational Inference with Normalizing Flows04.The Zoo of ion channelshttps://neuronstar.github.io/snm/04.the_zoo_of_ion_channels/Wed, 23 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/04.the_zoo_of_ion_channels/The Zoo of ion channelsReview of Normalizing Flowhttps://neuronstar.github.io/cpe/05.normalizing-flow-review/Sat, 30 Jan 2021 00:00:00 +0000https://neuronstar.github.io/cpe/05.normalizing-flow-review/Topics Normalizing flow Applications of normalizing flow Methods of normalizing flow Problems of normalizing flow05.Synapse and receptorhttps://neuronstar.github.io/snm/05.synapse_and_receptors/Mon, 28 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/05.synapse_and_receptors/Synapse and receptorDeep AutoRegressive Networkshttps://neuronstar.github.io/cpe/06.deep-autoregressive-networks/Sat, 13 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/06.deep-autoregressive-networks/Topics Refer to references.
Notes 1310.8499_notes.pdf06.Cable Equation and Its Solutionshttps://neuronstar.github.io/snm/06.cable_equation_and_its_solutions/Sat, 02 Apr 2016 00:00:00 +0000https://neuronstar.github.io/snm/06.cable_equation_and_its_solutions/Cable Equation and Its SolutionsMADE: Masked Autoencoder for Distribution Estimationhttps://neuronstar.github.io/cpe/07.made/Sat, 27 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/07.made/Topics Refer to references.
Notes 1310.8499_notes.pdf07.Two dimensional neuron modelshttps://neuronstar.github.io/snm/07.reduction_to_two_dimensions_and_phase_plane_analysis/Thu, 21 Apr 2016 00:00:00 +0000https://neuronstar.github.io/snm/07.reduction_to_two_dimensions_and_phase_plane_analysis/Two dimensional neuron modelsMAF: how is MADE being usedhttps://neuronstar.github.io/cpe/08.maf/Sat, 27 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/08.maf/We discussed MAF (arXiv:1705.07057v4) last time: The paper did not explain how exactly is MADE being used to update the shift and logscale.
We will use the tensorflow implementation of MAF to probe the above question. Here is the link to the relevant documentation: https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/MaskedAutoregressiveFlow
Topics Refer to references.
Notes 1310.8499_notes.pdf08.Integrate and Fire Models Part 1https://neuronstar.github.io/snm/08.integrate-and-fire-models-1/Sat, 21 May 2016 00:00:00 +0000https://neuronstar.github.io/snm/08.integrate-and-fire-models-1/Integrate and Fire Model Part 1Summary of Generative Modelshttps://neuronstar.github.io/cpe/09.summary-of-generative-models/Sat, 27 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/09.summary-of-generative-models/09.Reduction of the Hodgkin-Huxley model type IIhttps://neuronstar.github.io/snm/09.from_detailed_models_to_formal_spiking_neurons/Sat, 25 Jun 2016 00:00:00 +0000https://neuronstar.github.io/snm/09.from_detailed_models_to_formal_spiking_neurons/Reduction of the Hodgkin-Huxley model ‘type II’Energy-based Modelshttps://neuronstar.github.io/cpe/10.energy-based-learning/Sat, 27 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/10.energy-based-learning/We will discuss energy-based learning in this session.
References:
Lecture notes: https://atcold.github.io/pytorch-Deep-Learning/[cid:90ae645c-415b-4c9f-8ea6-c78839a8e8d4] https://atcold.github.io/pytorch-Deep-Learning/en/week07/07-1/ https://atcold.github.io/pytorch-Deep-Learning/en/week07/07-2/ https://drive.google.com/file/d/1z8Dz1YtkOEJpU-gh5RIjORs3GGqkYJQa/view : if you can not access Google Drive, this file (007-ebm-01) has been attached to this calendar event too. Supplementary:
https://arxiv.org/pdf/1803.08823.pdf10.Information Codinghttps://neuronstar.github.io/snm/10.noise_and_renewal_process/Sat, 25 Jun 2016 00:00:00 +0000https://neuronstar.github.io/snm/10.noise_and_renewal_process/Information codingEnergy-based Models 2https://neuronstar.github.io/cpe/11.energy-based-learning-2/Sat, 27 Feb 2021 00:00:00 +0000https://neuronstar.github.io/cpe/11.energy-based-learning-2/We will discuss energy-based learning in this session.
References:
Lecture notes: https://atcold.github.io/pytorch-Deep-Learning/[cid:90ae645c-415b-4c9f-8ea6-c78839a8e8d4] https://atcold.github.io/pytorch-Deep-Learning/en/week07/07-1/ https://atcold.github.io/pytorch-Deep-Learning/en/week07/07-2/ https://drive.google.com/file/d/1z8Dz1YtkOEJpU-gh5RIjORs3GGqkYJQa/view : if you can not access Google Drive, this file (007-ebm-01) has been attached to this calendar event too. Supplementary:
https://arxiv.org/pdf/1803.08823.pdf11.Renewal Theoryhttps://neuronstar.github.io/snm/11.stationary_renewal_theory/Tue, 05 Jul 2016 00:00:00 +0000https://neuronstar.github.io/snm/11.stationary_renewal_theory/Renewal TheoryEnergy-based Models 3https://neuronstar.github.io/cpe/12.energy-based-learning-3/Sat, 24 Apr 2021 00:00:00 +0000https://neuronstar.github.io/cpe/12.energy-based-learning-3/In the past two meetups, we have been discussing EBM from a computer scientist’s perspective.
In this discussion, we will discuss chapter XV of Mehta P, Bukov M, Wang C-HH, Day AGRR, Richardson C, Fisher CK, et al. A high-bias, low-variance introduction to Machine Learning for physicists. Phys Rep. 2018;810: 122. doi:10.1016/j.physrep.2019.03.00109.Escape Noisehttps://neuronstar.github.io/snm/12.escape_noise/Fri, 29 Jul 2016 00:00:00 +0000https://neuronstar.github.io/snm/12.escape_noise/Escape NoiseEnergy-based Models 4https://neuronstar.github.io/cpe/13.energy-based-learning-4/Wed, 26 May 2021 00:00:00 +0000https://neuronstar.github.io/cpe/13.energy-based-learning-4/In this discussion, we will discuss the Pytorch Deep Learning Lectures by LeCun.13.Comparison Between Neuron Modelshttps://neuronstar.github.io/snm/13.all_neuron_models/Tue, 05 Jul 2016 00:00:00 +0000https://neuronstar.github.io/snm/13.all_neuron_models/Comparison Between Neuron ModelsEnergy-based Models 5https://neuronstar.github.io/cpe/14.energy-based-learning-5/Wed, 02 Jun 2021 00:00:00 +0000https://neuronstar.github.io/cpe/14.energy-based-learning-5/In this meetup, we will discuss Restricted Boltzmann Machine (RBM). We will cover the reason for introducing RBM and the training. At the end of the discussion, we will also cover some topics of Deep Boltzmann Machines.14.Noise in Refractory Kernel and Diffusive Noisehttps://neuronstar.github.io/snm/14.slow-noise/Fri, 22 Jul 2016 00:00:00 +0000https://neuronstar.github.io/snm/14.slow-noise/Slow Noise in parameters and diffusive noise (Part 1)Predictive Coding Approximates Backprop along Arbitrary Computation Graphshttps://neuronstar.github.io/cpe/15.predictive-coding/Mon, 21 Jun 2021 00:00:00 +0000https://neuronstar.github.io/cpe/15.predictive-coding/In this meetup, we will discuss this paper: https://arxiv.org/abs/2006.04182
Why? Feedforward-backprop usually has a loss function that involves all the parameters. Backprop means we need this huge global loss $\mathcal L({w_{ij}})$. However, it is hard to imaging such global loss calculations in our brain. One of the alternatives is predictive coding, which only utilizes local connection information.
In this paper (2006.04182), the author proves the equivalence of backprop and predictive coding on arbitary graph.15.Diffusive Noise and The Subthreshold Regimehttps://neuronstar.github.io/snm/15.diffusive_noise_and_the_subthreshold_regime/Fri, 29 Jul 2016 00:00:00 +0000https://neuronstar.github.io/snm/15.diffusive_noise_and_the_subthreshold_regime/Diffusive Noise and The subthreshold RegimeLTD/LTPhttps://neuronstar.github.io/cpe/16.ltd-ltp/Mon, 21 Jun 2021 00:00:00 +0000https://neuronstar.github.io/cpe/16.ltd-ltp/In this meetup, we will discuss some key ideas related to biological neural network: LTP and LTD.16.stochastic processhttps://neuronstar.github.io/snm/16.stochastic_process/Fri, 05 Aug 2016 00:00:00 +0000https://neuronstar.github.io/snm/16.stochastic_process/stochastic processSelf-supervised Learning: Generative or Contrastivehttps://neuronstar.github.io/cpe/17.self-supervised-learning/Sat, 03 Jul 2021 00:00:00 +0000https://neuronstar.github.io/cpe/17.self-supervised-learning/Liu X, Zhang F, Hou Z, Wang Z, Mian L, Zhang J, et al. Self-supervised Learning: Generative or Contrastive. arXiv [cs.LG]. 2020. Available: http://arxiv.org/abs/2006.08218
We have discussed many topics of generative models. This paper serves as a summary of the current season of the discussions.17.Homogeneous Networkhttps://neuronstar.github.io/snm/17.homogeneous-network/Fri, 02 Sep 2016 00:00:00 +0000https://neuronstar.github.io/snm/17.homogeneous-network/Review of population activity; Homogeneous network.Self-supervised Learning: GANhttps://neuronstar.github.io/cpe/18.self-supervised-learning-gan/Sun, 01 Aug 2021 00:00:00 +0000https://neuronstar.github.io/cpe/18.self-supervised-learning-gan/We will discuss the reset of the paper arXiv:2006.08218.18.SRM with Escape Noisehttps://neuronstar.github.io/snm/18.population-srm-with-escape-noise/Fri, 23 Sep 2016 00:00:00 +0000https://neuronstar.github.io/snm/18.population-srm-with-escape-noise/SRM neurons with escape noiseSelf-supervised Learning: Theories (Part 1)https://neuronstar.github.io/cpe/19.self-supervised-learning-theories-1/Thu, 26 Aug 2021 00:00:00 +0000https://neuronstar.github.io/cpe/19.self-supervised-learning-theories-1/We will discuss Section 6 of the paper arXiv:2006.08218.19.Population Activityhttps://neuronstar.github.io/snm/19.population-activity/Fri, 30 Sep 2016 00:00:00 +0000https://neuronstar.github.io/snm/19.population-activity/Integral equations for population activitySelf-supervised Learning: Theories (Part 2)https://neuronstar.github.io/cpe/20.self-supervised-learning-theories-2/Thu, 26 Aug 2021 00:00:00 +0000https://neuronstar.github.io/cpe/20.self-supervised-learning-theories-2/We will dive deep into Section 6 of the paper arXiv:2006.08218. Here are a few topics to be explored.
InfoGAN objective; Positive and negative samples in loss function (InfoNCE); Uniformity in constrastive loss; JS-divergence.20.Basics of Renewal Theoryhttps://neuronstar.github.io/snm/20.basics-of-renewal-theory/Sat, 08 Oct 2016 00:00:00 +0000https://neuronstar.github.io/snm/20.basics-of-renewal-theory/from math to neuroscienceGraph Neural Networks: Basicshttps://neuronstar.github.io/cpe/21.gnn-basics/Sat, 11 Sep 2021 00:00:00 +0000https://neuronstar.github.io/cpe/21.gnn-basics/This will be the beginning of a new topic: Graph Neural Networks. In this new series, we will use the textbook by Hamilton1. For the first episode, we will discuss some basics about graphs to make sure we are all on the same page.
@Steven will lead the discussion.
Hamilton2020 Hamilton WL. Graph representation learning. Synth lect artif intell mach learn. 2020;14: 1–159. doi:10.2200/s01045ed1v01y202009aim046 ↩︎21.Asynchronous Firinghttps://neuronstar.github.io/snm/21.asynchronous-firing/Fri, 14 Oct 2016 00:00:00 +0000https://neuronstar.github.io/snm/21.asynchronous-firing/Asynchronous firing of homogeneous networkGraph Neural Networks: Basics (2)https://neuronstar.github.io/cpe/22.gnn-basics-2/Sun, 03 Oct 2021 00:00:00 +0000https://neuronstar.github.io/cpe/22.gnn-basics-2/We will continue the discussion on Graph Neural Networks.
Problems of using Graphs Graph Neural Networks Textbook: Hamilton1
Hamilton2020 Hamilton WL. Graph representation learning. Synth lect artif intell mach learn. 2020;14: 1–159. doi:10.2200/s01045ed1v01y202009aim046 ↩︎22.interacting populations and continuum modelshttps://neuronstar.github.io/snm/22.interacting-populations-and-continuum-models/Sat, 29 Oct 2016 00:00:00 +0000https://neuronstar.github.io/snm/22.interacting-populations-and-continuum-models/network of networks and continuum networkGraph Neural Networkshttps://neuronstar.github.io/cpe/23.gnn/Tue, 19 Oct 2021 00:00:00 +0000https://neuronstar.github.io/cpe/23.gnn/Chapter 5 of Hamilton1.
Hamilton2020 Hamilton WL. Graph representation learning. Synth lect artif intell mach learn. 2020;14: 1–159. doi:10.2200/s01045ed1v01y202009aim046 ↩︎23.Linearized Population Equation and Transientshttps://neuronstar.github.io/snm/23.linearized-population-equation/Fri, 11 Nov 2016 00:00:00 +0000https://neuronstar.github.io/snm/23.linearized-population-equation/The population equation is quite complicated to solve, hence we linearize it and inspect the perturbation theory.Graph Neural Networks: PyTorchhttps://neuronstar.github.io/cpe/24.gnn-pytorch/Tue, 02 Nov 2021 00:00:00 +0000https://neuronstar.github.io/cpe/24.gnn-pytorch/We will go through the GNN tutorial by Phillip Lippe.24. From individual neurons to collective burstinghttps://neuronstar.github.io/snm/24.from_individual_neurons_to_collective_bursting/Wed, 16 Nov 2016 00:00:00 +0000https://neuronstar.github.io/snm/24.from_individual_neurons_to_collective_bursting/Predicting collective dynamics from individual neuron properties.Graph Neural Networks: Theoretical Motivationshttps://neuronstar.github.io/cpe/25.gnn-2/Fri, 12 Nov 2021 00:00:00 +0000https://neuronstar.github.io/cpe/25.gnn-2/We have changed the time!25. The Significance of Single Spikehttps://neuronstar.github.io/snm/25.significance-of-single-spike/Fri, 09 Dec 2016 00:00:00 +0000https://neuronstar.github.io/snm/25.significance-of-single-spike/Single spike can have dramatic consequences on population activity.Graph Neural Networks: Theoretical Motivations (Part 2)https://neuronstar.github.io/cpe/26.gnn-3/Fri, 12 Nov 2021 00:00:00 +0000https://neuronstar.github.io/cpe/26.gnn-3/We discussed the first section of Chapter 7. In this event, we will continue discussing chapter 7 of Hamilton1.
In this chapter, we will visit some of the theoretical underpinnings of graph neu- ral networks (GNNs). One of the most intriguing aspects of GNNs is that they were independently developed from distinct theoretical motivations.
Click here for an interactive widget.
Hamilton2020 Hamilton WL.Graph Convolutional Matrix Completionhttps://neuronstar.github.io/cpe/27.graph-convolutional-matrix-completion/Sat, 11 Dec 2021 00:00:00 +0000https://neuronstar.github.io/cpe/27.graph-convolutional-matrix-completion/Our topic for this session is Graph Convolutional Matrix Completion (arXiv:1706.02263).
Abstract
Abstract of Graph Convolutional Matrix Completion (arXiv:1706.02263):
We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with labeled edges denoting observed ratings. Building on recent progress in deep learning on graph-structured data, we propose a graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph.27. Synchronized Oscillations and Lockinghttps://neuronstar.github.io/snm/27.synchronized-oscillations-and-locking/Fri, 03 Feb 2017 00:00:00 +0000https://neuronstar.github.io/snm/27.synchronized-oscillations-and-locking/LockingMultivariate Time-series Forecasting Using GNNhttps://neuronstar.github.io/cpe/28.gnn-time-series-forecasting/Sat, 11 Dec 2021 00:00:00 +0000https://neuronstar.github.io/cpe/28.gnn-time-series-forecasting/Our topic for this session is Spectral Temporal Graph Neural Network for multivariate time-series forecasting (arXiv:2103.07719).
Abstract
Abstract of Spectral Temporal Graph Neural Network for multivariate time-series forecasting (arXiv:2103.07719):
Multivariate time-series forecasting plays a crucial rolein many real-world ap-plications. It is a challenging problem as one needs to consider both intra-seriestemporal correlations and inter-series correlations simultaneously. Recently, there have been multiple works trying to capture both correlations, but most, if not allof them only capture temporal correlations in the time domain and resort to pre-defined priors as inter-series relationships.28. Oscillations in Reverberating Loopshttps://neuronstar.github.io/snm/28.oscillations-in-reverberating-loops/Fri, 17 Feb 2017 00:00:00 +0000https://neuronstar.github.io/snm/28.oscillations-in-reverberating-loops/Oscillations in reverberating loops can be simplified and researched.Hamilton WL. Graph Representation Learning. Chapter 8https://neuronstar.github.io/cpe/29.hamilton-traditional-graph-generation-approaches/Sat, 05 Feb 2022 00:00:00 +0000https://neuronstar.github.io/cpe/29.hamilton-traditional-graph-generation-approaches/Our topic for this session is Chapter 8 of Hamilton WL. Graph Representation Learning: Traditional GraphGeneration Approaches.
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.29. Hebbian Learninghttps://neuronstar.github.io/snm/29.hebbian-learning/Sat, 06 May 2017 00:00:00 +0000https://neuronstar.github.io/snm/29.hebbian-learning/Simplest learning rule, aka, correlation based learningHamilton WL. Graph Representation Learning. Chapter 8 (2)https://neuronstar.github.io/cpe/30.hamilton-traditional-graph-generation-approaches-2/Fri, 18 Feb 2022 00:00:00 +0000https://neuronstar.github.io/cpe/30.hamilton-traditional-graph-generation-approaches-2/We will wrap up Chapter 8 of Hamilton WL. Graph Representation Learning: Graph Generation.
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.30. Learning Equationshttps://neuronstar.github.io/snm/30.learning-equations/Sat, 03 Jun 2017 00:00:00 +0000https://neuronstar.github.io/snm/30.learning-equations/Unsupervised learningUncertainty in Deep Learninghttps://neuronstar.github.io/cpe/31.uncertaintyt-in-deep-learning/Sat, 26 Feb 2022 00:00:00 +0000https://neuronstar.github.io/cpe/31.uncertaintyt-in-deep-learning/Topic: uncertainty in deep learning
References:
Gawlikowski, J. et al. A Survey of Uncertainty in Deep Neural Networks. Arxiv (2021). Jospin, L. V., Buntine, W., Boussaid, F., Laga, H. & Bennamoun, M. Hands-on Bayesian Neural Networks – a Tutorial for Deep Learning Users. Arxiv (2020). Gal, Yarin. “Uncertainty in deep learning.” (2016): 3. Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.31. Plasticity and Codinghttps://neuronstar.github.io/snm/31.plasticity-and-coding/Sat, 10 Jun 2017 00:00:00 +0000https://neuronstar.github.io/snm/31.plasticity-and-coding/How is plasticity related to neuronal codingCausal Inferencehttps://neuronstar.github.io/cpe/35.causal-inference/Mon, 09 May 2022 00:00:00 +0000https://neuronstar.github.io/cpe/35.causal-inference/Alexa will lead a discussion on causal inference.
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Counterfactual Explanation in Multivariate Time Serieshttps://neuronstar.github.io/cpe/34.counterfactual-prediction-multivariate-time-series/Tue, 12 Apr 2022 00:00:00 +0000https://neuronstar.github.io/cpe/34.counterfactual-prediction-multivariate-time-series/Ates E, Aksar B, Leung VJ, Coskun AK. Counterfactual Explanations for Machine Learning on Multivariate Time Series Data. arXiv [cs.LG]. 2020. Available: http://arxiv.org/abs/2008.10781
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Review of Time Series Forecastinghttps://neuronstar.github.io/cpe/33.review-of-timeseries-2/Tue, 12 Apr 2022 00:00:00 +0000https://neuronstar.github.io/cpe/33.review-of-timeseries-2/Lim B, Zohren S. Time Series Forecasting With Deep Learning: A Survey. arXiv [stat.ML]. 2020. Available: http://arxiv.org/abs/2004.13408
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Conformal Time Series Forecastinghttps://neuronstar.github.io/cpe/32.review-of-timeseries/Thu, 10 Mar 2022 00:00:00 +0000https://neuronstar.github.io/cpe/32.review-of-timeseries/We start our new journey on time series by sharing and discussing two review papers:
Lim B, Zohren S. Time Series Forecasting With Deep Learning: A Survey. arXiv [stat.ML]. 2020. Available: http://arxiv.org/abs/2004.13408 Gneiting T, Katzfuss M. Probabilistic Forecasting. Annu Rev Stat Appl. 2014;1: 125–151. doi:10.1146/annurev-statistics-062713-085831 (pdf) Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Evaluating time series forecasting modelshttps://neuronstar.github.io/cpe/36.evaluating-forecasting-models/Fri, 10 Jun 2022 00:00:00 +0000https://neuronstar.github.io/cpe/36.evaluating-forecasting-models/Our topic for this session is
Cerqueira V, Torgo L, Mozetic I. Evaluating time series forecasting models: An empirical study on performance estimation methods. arXiv [cs.LG]. 2019. Available: http://arxiv.org/abs/1905.11744
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.DeepARhttps://neuronstar.github.io/cpe/37.deepar/Fri, 10 Jun 2022 00:00:00 +0000https://neuronstar.github.io/cpe/37.deepar/Topic: DeepAR.
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Temporal Fusion Transformerhttps://neuronstar.github.io/cpe/38.tft/Sat, 09 Jul 2022 00:00:00 +0000https://neuronstar.github.io/cpe/38.tft/Lim B, Arik SO, Loeff N, Pfister T. Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting. In: arXiv.org [Internet]. 19 Dec 2019 [cited 9 Jul 2022]. Available: https://arxiv.org/abs/1912.09363
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Data Augmentation for Time Serieshttps://neuronstar.github.io/cpe/39.data-augmentation-ts/Mon, 01 Aug 2022 00:00:00 +0000https://neuronstar.github.io/cpe/39.data-augmentation-ts/Wen Q, Sun L, Yang F, Song X, Gao J, Wang X, et al. Time Series Data Augmentation for Deep Learning: A Survey. arXiv [cs.LG]. 2020. Available: http://arxiv.org/abs/2002.12478
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.M Competitionhttps://neuronstar.github.io/cpe/40.m-competition/Sun, 07 Aug 2022 00:00:00 +0000https://neuronstar.github.io/cpe/40.m-competition/We will discuss the M competition.
@小紫花:
M5: 2020 年的一个比赛，预测沃尔玛在米国 3 个州、 10 个店、3000 多个产品的销售，要求预测 28 天。两个比赛：预测一个中值，或者预测一个分布（9 个数）。今年有 M6 官网，指引 PDF https://mofc.unic.ac.cy/m5-competition/ 中值 https://www.kaggle.com/competitions/m5-forecasting-accuracy/ 分布 https://www.kaggle.com/competitions/m5-forecasting-uncertainty 比赛背景、组织、运营总结 https://www.sciencedirect.com/science/article/pii/S0169207021001187 中值预测总结 https://www.sciencedirect.com/science/article/pii/S0169207021001874 分布预测总结（我比较感兴趣） https://www.sciencedirect.com/science/article/pii/S0169207021001722 一篇评论文章 https://www.sciencedirect.com/science/article/abs/pii/S016920702100128X 对讨论的回复 https://www.sciencedirect.com/science/article/abs/pii/S0169207022000644
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Neural ODEhttps://neuronstar.github.io/cpe/41.neural-ode/Mon, 22 Aug 2022 00:00:00 +0000https://neuronstar.github.io/cpe/41.neural-ode/Topic:
Chen RTQ, Rubanova Y, Bettencourt J, Duvenaud D. Neural Ordinary Differential Equations. arXiv [cs.LG]. 2018. Available: http://arxiv.org/abs/1806.07366
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Gradient Boosted Decision Trees (I)https://neuronstar.github.io/cpe/42.gbdt-1/Mon, 22 Aug 2022 00:00:00 +0000https://neuronstar.github.io/cpe/42.gbdt-1/Topic: XGBoost, LightGBM and Trees (I)
References: https://xgboost.readthedocs.io/en/stable/tutorials/model.html
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Gradient Boosted Decision Trees (II)https://neuronstar.github.io/cpe/43.gbdt-2/Mon, 22 Aug 2022 00:00:00 +0000https://neuronstar.github.io/cpe/43.gbdt-2/Topic: XGBoost, LightGBM and Trees (II)
References:
https://lightgbm.readthedocs.io/en/v3.3.2/ https://papers.nips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Forecasting with Treeshttps://neuronstar.github.io/cpe/44.forecasting-with-trees/Sun, 16 Oct 2022 00:00:00 +0000https://neuronstar.github.io/cpe/44.forecasting-with-trees/Topic: Forecasting with Trees
References:
https://www.sciencedirect.com/science/article/pii/S0169207021001679 Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Probabilistic Forecasting: A Level-Set Approachhttps://neuronstar.github.io/cpe/45.level-set-forecaster/Fri, 11 Nov 2022 00:00:00 +0000https://neuronstar.github.io/cpe/45.level-set-forecaster/Topic:
Hasson H, Wang Y, Januschowski T, Gasthaus J. Probabilistic forecasting: A level-set approach. [cited 25 Jan 2022]. Available: https://assets.amazon.science/a7/2b/29e00a5e429b8f2e708091ecb53e/probabilistic-forecasting-a-level-set-approach.pdf
Code: https://github.com/awslabs/gluonts/blob/fcc50e8be222bcf3b3da47ed1ed50b467e03f7e8/src/gluonts/ext/rotbaum/_model.py
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Diffusion Models: A Comprehensive Survey of Methods and Applicationshttps://neuronstar.github.io/cpe/46.difussion-model/Wed, 23 Nov 2022 00:00:00 +0000https://neuronstar.github.io/cpe/46.difussion-model/Topic:
Yang L, Zhang Z, Song Y, Hong S, Xu R, Zhao Y, et al. Diffusion Models: A Comprehensive Survey of Methods and Applications. arXiv [cs.LG]. 2022. Available: http://arxiv.org/abs/2209.00796
Use the following timezone tool or click on the “Add to Calendar” button on the sidebar.
Click here for an interactive widget.Inferring causal impact using Bayesian structural time-series modelshttps://neuronstar.github.io/cpe/tbd.causal-impact-bayesian-structural-ts-models/Sat, 21 May 2022 00:00:00 +0000https://neuronstar.github.io/cpe/tbd.causal-impact-bayesian-structural-ts-models/Our topic for this session is Inferring causal impact using Bayesian structural time-series models (arXiv:1506.00356).
Abstract
Abstract of Inferring causal impact using Bayesian structural time-series models (arXiv:1506.00356):
An important problem in econometrics and marketing is to infer the causal impact that a designed market intervention has exerted on an outcome metric over time. This paper proposes to infer causal impact on the basis of a diffusion-regression state-space model that predicts the counterfactual market response in a synthetic control that would have occurred had no intervention taken place.References for Probability Estimation Clubhttps://neuronstar.github.io/cpe/00.references/Sat, 12 Dec 2020 00:00:00 +0000https://neuronstar.github.io/cpe/00.references/A list of references for our online discussions.Conditional Probability Estimationhttps://neuronstar.github.io/projects/conditional-probability-estimation/Tue, 03 Nov 2020 00:00:00 +0000https://neuronstar.github.io/projects/conditional-probability-estimation/Understand models to estimate conditional probabilitiesFoundations of Machine Learninghttps://neuronstar.github.io/projects/ml-foundations/Sun, 03 May 2020 00:00:00 +0000https://neuronstar.github.io/projects/ml-foundations/Dive deep into the foundations of machine learning.Spiking Neuron Modelshttps://neuronstar.github.io/projects/snm/Mon, 27 Apr 2020 13:22:46 +0200https://neuronstar.github.io/projects/snm/Reading club for the book Spiking Neuron ModelsThe Elements of Statistical Learning Reading Clubhttps://neuronstar.github.io/projects/esl/Mon, 27 Apr 2020 13:22:46 +0200https://neuronstar.github.io/projects/esl/Read the book05.Least Angle Regressionhttps://neuronstar.github.io/esl/05.least-angle-regression/Thu, 29 Sep 2016 00:00:00 +0000https://neuronstar.github.io/esl/05.least-angle-regression/Least angle regression, aka, LAR04.Shrinkage Methodshttps://neuronstar.github.io/esl/04.shrinkage-methods/Fri, 23 Sep 2016 00:00:00 +0000https://neuronstar.github.io/esl/04.shrinkage-methods/Shrinkage methods03.Guass-Markov Theorem and Multiple Regressionhttps://neuronstar.github.io/esl/03.gauss-markov-theorem/Thu, 01 Sep 2016 00:00:00 +0000https://neuronstar.github.io/esl/03.gauss-markov-theorem/Gauss-Markov Theorem02.Linear Methods for Regressionhttps://neuronstar.github.io/esl/02.linear-methods-for-regresssion/Thu, 18 Aug 2016 00:00:00 +0000https://neuronstar.github.io/esl/02.linear-methods-for-regresssion/Linear regression, least squares01.Introductions (Review) and Several Preliminary Statistical Methodshttps://neuronstar.github.io/esl/01.statistical-learning-theory/Wed, 06 Jul 2016 00:00:00 +0000https://neuronstar.github.io/esl/01.statistical-learning-theory/Some basics of statistical learning; least squares and k nearest neighbors; statistical decision theory; local methods in high dimensionsABOUThttps://neuronstar.github.io/about/Thu, 24 Mar 2016 00:00:00 +0000https://neuronstar.github.io/about/We host reading clubs and seminars on neuroscience, machine learning, complex networks and intelligence.
License & Source Articles on this website are published under CC BY-NC-SA license if no specific license is designated.
This website is hosted on GitHub and generated by GitHub Pages (hugo). Computational Neuroscience Map is written in TiddlyMap and hosted statically on GitHub Pages.00.Spiking Neuron Models Reading Clubhttps://neuronstar.github.io/snm/00.spiking_neuron_models_club/Fri, 18 Mar 2016 00:00:00 +0000https://neuronstar.github.io/snm/00.spiking_neuron_models_club/Introduction to reading club of spiking neuron models, schedule, and notice00.The Elements of Statistical Learning Reading Clubhttps://neuronstar.github.io/esl/00.the-elements-of-statistical-learning/Fri, 18 Mar 2016 00:00:00 +0000https://neuronstar.github.io/esl/00.the-elements-of-statistical-learning/Introduction to reading club of The Elements of Statistical Learning, schedule, and notice<link>https://neuronstar.github.io/esl/readme/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://neuronstar.github.io/esl/readme/</guid><description>elements-of-statistical-learning Reading club: The Elements of Statistical Learning
Online Course: StatLearning@Standford
An Introductory Book: http://www-bcf.usc.edu/~gareth/ISL/ISLR%20Seventh%20Printing.pdf http://www.dataschool.io/15-hours-of-expert-machine-learning-videos/ The easiest way of creating notes is to duplicate one of the previous .md files and make changes to it.
Code of conduct:
Create a markdown file with extension .md; Any file name works, however, file names begins with two-digit number would be a nice convention. The markdown file has to include a header session that specifies the meta data.</description></item><item><title/><link>https://neuronstar.github.io/typography/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://neuronstar.github.io/typography/</guid><description>ToC {:toc} We use kramdown This website uses kramdown as the basic syntax. However, a lot of html/css/js has been applied to generate some certain contents or styles.
Math also follows the kramdown syntax.
Footnote Syntax for footnotes is elaborated more on the website of kramdown.
{% highlight text %} Some text here some other text here.1
Table of Contents {% highlight text %}
ToC {:toc} {% endhighlight %} is used to generate table of contents.</description></item></channel></rss>