{"id":21320521,"url":"https://github.com/tkusmierczyk/machine_learning_demos","last_synced_at":"2025-09-23T20:59:59.547Z","repository":{"id":68115752,"uuid":"192549174","full_name":"tkusmierczyk/machine_learning_demos","owner":"tkusmierczyk","description":"Notebooks and code snippets demonstrating machine learning techniques.","archived":false,"fork":false,"pushed_at":"2024-10-29T14:27:58.000Z","size":5836,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-10-29T17:11:30.107Z","etag":null,"topics":["bayesian-optimization","global-optimization","machine-learning"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tkusmierczyk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-06-18T13:48:17.000Z","updated_at":"2024-10-29T14:28:07.000Z","dependencies_parsed_at":"2024-01-04T21:47:44.872Z","dependency_job_id":null,"html_url":"https://github.com/tkusmierczyk/machine_learning_demos","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tkusmierczyk%2Fmachine_learning_demos","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tkusmierczyk%2Fmachine_learning_demos/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tkusmierczyk%2Fmachine_learning_demos/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tkusmierczyk%2Fmachine_learning_demos/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tkusmierczyk","download_url":"https://codeload.github.com/tkusmierczyk/machine_learning_demos/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225795387,"owners_count":17525316,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bayesian-optimization","global-optimization","machine-learning"],"created_at":"2024-11-21T19:48:09.703Z","updated_at":"2025-09-23T20:59:59.526Z","avatar_url":"https://github.com/tkusmierczyk.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":" # Machine Learning Demos\n\nNotebooks and code snippets demonstrating various machine learning techniques:\n\n9. [Three approaches for computing trace of hessian for i-th output of a PyTorch module](trace_of_hessian_for_model_output.ipynb)\n * Hessian computation using autograd\n * Hessian computation using Laplace library\n * Trace of Hessian computation using the Hutchinson's estimator\n\n8. [PyTorch implementation of SNGP (Spectral-normalized Neural Gaussian Process) and comparison against VBLL](sngp_pytorch.ipynb)\n * Implementation of SpectralNormalization wrapper\n * Implementation of RandomFeatureGaussianProcess\n * Implementation of DeepResNet SNGP\n * Test of replacing classification head with [VBLL layers](https://github.com/VectorInstitute/vbll/)\n\n7. [Bias of predictive mean calculated with averages of Dropout layers](dropout_bnn_mean.ipynb)\n * Compare predictive means calculated by averaging samples from a BNN vs output calculated for Dropout averages. \n\n6. [Comparison of REINFORCE vs Gumbel-Softmax vs MDNF gradients and convergence for a simplified objective](reinforce_vs_gumbelsoftmax_gradients.ipynb)\n * Optimization using REINFORCE vs reparametrization gradients (with GradientTape)\n * Gumbel-Softmax relaxation for discrete variables - an illustration of a bias\n * Mixture of Discrete Normalizing Flows relaxation for discrete variables\n \n5. [Illustration of how entropy of the relaxed categorical distribution can be estimated and utilized for VI](entropy_of_relaxed_categorical_distribution.ipynb)\n * Comparison (and discussion of gradients) of three estimates of the entropy/KL-term in ELBO \n\n4. [Variational Autoencoder using Relaxed Categorical distribution](vae_relaxed_categorical.ipynb)\n * Sampling from Gumbel softmax with and without straight-through\n * Implementation of different approaches to estimation of KL divergence\n * Training with Mnist data\n * Reconstruction of digits and unconditional sampling latent codes\n\n3. [A demonstration of Discrete Flows: Invertible Generative Models of Discrete Data](discrete_flows.ipynb)\n * Arithmetic on one-hot encoded vectors\n * Trainig simple discrete transformation\n * MLE-training of an autoregressive flow with masked autoencoder to match a target distribution.\n\n2. [Probabilistc Matrix Factorization model with mean-field variational inference](probabilisitc_matrix_factorization_vi.ipynb).\n * Probabilistc Matrix Factorization implementation\n * estimating ELBO using MC\n * training using pyTorch automatic differentiation\n * simple evaluation of RMSE on test subset \n\n1. [Framing multi-output Bayesian optimization with GPyOpt](multi-task_bayesian_optimization_demo.ipynb)\n * fitting individual GPs \n * fitting multi-task GPs using coregionalization\n * BO optimization of single function\n * BO optimization of 2-task problem\n * An implementation of a custom acquisition function\n * Extensive visualization of the optimization process\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftkusmierczyk%2Fmachine_learning_demos","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftkusmierczyk%2Fmachine_learning_demos","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftkusmierczyk%2Fmachine_learning_demos/lists"}