{"id":16509323,"url":"https://github.com/mohd-faizy/probabilistic-deep-learning-with-tensorflow","last_synced_at":"2025-10-07T13:04:19.454Z","repository":{"id":49586548,"uuid":"313710066","full_name":"mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow","owner":"mohd-faizy","description":"Probabilistic Deep Learning finds its application in autonomous vehicles and medical diagnoses. This is an increasingly important area of deep learning that aims to quantify the noise and uncertainty that is often present in real-world datasets.","archived":false,"fork":false,"pushed_at":"2025-09-12T21:08:10.000Z","size":81161,"stargazers_count":70,"open_issues_count":0,"forks_count":34,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-12T22:41:56.728Z","etag":null,"topics":["bernoulli-distribution","binomial-distributions","deep-probabilistic-models","keras","machine-learning","multivariate-distributions","poisson-distribution","probabilistic-deep-learning","probabilistic-layers","probabilistic-programming","tensorflow","tensorflow-probability","tensorflow2","tfp","univariate-distributions"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mohd-faizy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2020-11-17T18:38:39.000Z","updated_at":"2025-09-12T21:08:13.000Z","dependencies_parsed_at":"2023-01-19T23:16:58.284Z","dependency_job_id":"91cc6242-46b3-434e-9997-cd187f793bc2","html_url":"https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FProbabilistic-Deep-Learning-with-TensorFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FProbabilistic-Deep-Learning-with-TensorFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FProbabilistic-Deep-Learning-with-TensorFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FProbabilistic-Deep-Learning-with-TensorFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mohd-faizy","download_url":"https://codeload.github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohd-faizy%2FProbabilistic-Deep-Learning-with-TensorFlow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278778975,"owners_count":26044259,"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","status":"online","status_checked_at":"2025-10-07T02:00:06.786Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["bernoulli-distribution","binomial-distributions","deep-probabilistic-models","keras","machine-learning","multivariate-distributions","poisson-distribution","probabilistic-deep-learning","probabilistic-layers","probabilistic-programming","tensorflow","tensorflow-probability","tensorflow2","tfp","univariate-distributions"],"created_at":"2024-10-11T15:49:58.312Z","updated_at":"2025-10-07T13:04:19.448Z","avatar_url":"https://github.com/mohd-faizy.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 **Probabilistic Deep Learning with TensorFlow**\n\n\u003cdiv align=\"center\"\u003e\n\n[![Author](https://img.shields.io/badge/Author-mohd--faizy-red?style=for-the-badge\u0026logo=github\u0026logoColor=white)](https://github.com/mohd-faizy)\n[![TensorFlow](https://img.shields.io/badge/TensorFlow-2.15%2B-FF6F00?style=for-the-badge\u0026logo=tensorflow\u0026logoColor=white)](https://tensorflow.org/)\n[![TensorFlow Probability](https://img.shields.io/badge/TensorFlow%20Probability-0.23%2B-FF6F00?style=for-the-badge\u0026logo=tensorflow\u0026logoColor=white)](https://www.tensorflow.org/probability)\n[![Platform](https://img.shields.io/badge/Platform-Jupyter%20Labs-blue?style=for-the-badge\u0026logo=jupyter\u0026logoColor=white)](https://jupyter.org/)\n[![Maintained](https://img.shields.io/maintenance/yes/2025?style=for-the-badge)](https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow)\n[![Last Commit](https://img.shields.io/github/last-commit/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow?style=for-the-badge\u0026logo=git\u0026logoColor=white)](https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow)\n[![GitHub Issues](https://img.shields.io/github/issues/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow?style=for-the-badge\u0026logo=github\u0026logoColor=white)](https://github.com/mohd-faizy/07T_Probabilistic-Deep-Learning-with-TensorFlow/issues)\n[![Stars](https://img.shields.io/github/stars/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow?style=for-the-badge\u0026logo=github\u0026logoColor=white)](https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow)\n[![License](https://img.shields.io/github/license/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow?style=for-the-badge\u0026logo=opensourceinitiative\u0026logoColor=white)](https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow/blob/master/LICENSE)\n[![Contributions Welcome](https://img.shields.io/badge/Contributions-Welcome-0059b3?style=for-the-badge\u0026logo=handshake\u0026logoColor=white)](https://github.com/mohd-faizy/07T_Probabilistic-Deep-Learning-with-TensorFlow)\n[![Repo Size](https://img.shields.io/github/repo-size/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow?style=for-the-badge\u0026logo=github\u0026logoColor=white)](https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow)\n\n\n\n\n\n\u003c/div\u003e\n\n\u003cimg src='https://raw.githubusercontent.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow/refs/heads/main/_img/head.png'\u003e\n\nThis repository is a comprehensive collection of **TensorFlow Probability** implementations for probabilistic deep learning. The *primary* goal is **educational**: to bridge the gap between traditional deterministic models and real-world uncertainty quantification. \n\n\n✨**Unlock the power of uncertainty quantification in machine learning.** \n\nThis repository provides hands-on implementations of probabilistic deep learning using TensorFlow Probability (TFP), enabling you to build models that not only make predictions but also quantify how confident they are about those predictions.\n\n\u003e **Documentation**: [TFP API Docs](https://www.tensorflow.org/probability/api_docs/python/tfp)\n\n\n\n## 🎯 Overview\n![tfp-map](https://raw.githubusercontent.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow/refs/heads/main/_img/tfp_map.png)\n\n### What Makes This Repository Special?\n\nTraditional machine learning models provide point estimates without quantifying uncertainty. In critical applications like medical diagnosis, autonomous vehicles, or financial modeling, **knowing how confident your model is** can be the difference between success and catastrophic failure.\n\n- Enables models to express confidence levels using probabilistic layers and Bayesian neural networks.\n\n- Supports sampling, log-likelihood evaluation, and manipulation of complex distributions (univariate \u0026 multivariate).\n\n- Powers VAEs and normalizing flows for density estimation, representation learning, and synthetic data generation.\n\nThis repository demonstrates how **TensorFlow Probability** transforms your standard neural networks into probabilistic powerhouses that:\n\n- **Quantify uncertainty** in predictions\n- **Model complex distributions** beyond simple Gaussian assumptions  \n- **Perform Bayesian inference** at scale\n- **Generate realistic synthetic data** through advanced generative models\n\n\n### Why Probabilistic Deep Learning Matters\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://youtu.be/BrwKURU-wpk?si=S0xhuUHoiYGaorcE\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow/refs/heads/main/_img/tfp_dev_summit_ytd.jpg\" width=\"500\" height=\"280\" alt=\"Description\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\n\nReal-world data is messy, incomplete, and uncertain. Probabilistic deep learning addresses these challenges by:\n\n- **Handling Data Scarcity**: Bayesian approaches work well with limited data.\n- **Robust Decision Making**: Uncertainty estimates guide better decisions.\n- **Interpretable AI**: Understanding model confidence builds trust\n- **Anomaly Detection**: Identifying outliers and unusual patterns.\n- **Risk Assessment**: Quantifying potential failure modes.\n\n\n#### ⚙️**Technical Strengths**\n- Bayesian neural networks: Adds priors to weights and calibrates predictive uncertainty for out-of-distribution robustness.\n\n- Normalizing flows: Uses invertible transforms for expressive density estimation and efficient sampling.\n\n- Variational inference: Optimizes ELBO with reparameterization for controllable generation and learning.\n\n#### 🚀**Trade-offs \u0026 Performance**\n- Higher memory and training time than deterministic models.\n- Gains in interpretability, calibrated risk, and anomaly detection often outweigh the cost\n\n\n---\n\n## 🔧 Prerequisites\n\n### Mathematical Background\n- **Linear Algebra**: Matrix operations, eigenvalues, SVD\n- **Calculus**: Derivatives, gradients, optimization\n- **Statistics**: Probability theory, Bayes' theorem, distributions\n- **Information Theory**: KL divergence, entropy, mutual information\n\n### Programming Skills\n- **Python 3.8+** with object-oriented programming\n- **TensorFlow/Keras** fundamentals\n- **NumPy/SciPy** for numerical computing\n- **Matplotlib/Seaborn** for visualization\n\n### Recommended Reading\n- [Pattern Recognition and Machine Learning](https://www.microsoft.com/en-us/research/people/cmbishop/#!prml-book) by Christopher Bishop\n- [The Elements of Statistical Learning](https://web.stanford.edu/~hastie/ElemStatLearn/) by Hastie, Tibshirani, and Friedman\n- [Probabilistic Machine Learning](https://probml.github.io/pml-book/) by Kevin Murphy\n\n---\n\n\n## 🚀 Quick Start\n\n1. **Clone the repository:**\n   ```bash\n   git clone https://github.com/mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow.git\n   cd Probabilistic-Deep-Learning-with-TensorFlow\n    ```\n\n2. **Create virtual environment (using [uv](https://github.com/astral-sh/uv) – ⚡ faster alternative):**\n\n   ```bash\n   # Install uv if not already installed\n   pip install uv\n\n   # Create and activate virtual environment\n   uv venv\n\n   # Activate the env\n   source .venv/bin/activate   # Linux/macOS\n   .venv\\Scripts\\activate      # Windows\n   ```\n\n3. **Install dependencies:**\n\n   ```bash\n   uv add -r requirements.txt\n   ```\n\n4. **Verify installation:**\n\n   ```python\n   import tensorflow as tf\n   import tensorflow_probability as tfp\n\n   print(f\"TensorFlow: {tf.__version__}\")\n   print(f\"TensorFlow Probability: {tfp.__version__}\")\n   ```\n\n---\n\n### ⚡ Quick Example\n\n```python\nimport tensorflow as tf\nimport tensorflow_probability as tfp\n\ntfd = tfp.distributions\n\n# Create a probabilistic model\ndef create_bayesian_model():\n    model = tf.keras.Sequential([\n        tfp.layers.DenseVariational(\n            units=64,\n            make_prior_fn=lambda: tfd.Normal(0., 1.),\n            make_posterior_fn=tfp.layers.default_mean_field_normal_fn(),\n            kl_weight=1/50000\n        ),\n        tf.keras.layers.Dense(10, activation='softmax')\n    ])\n    return model\n\n# Train with uncertainty quantification\nmodel = create_bayesian_model()\nmodel.compile(optimizer='adam', loss='sparse_categorical_crossentropy')\n```\n\n\n---\n\n## 🎲 Core Probability Distributions\n\nUnderstanding these distributions is crucial for effective probabilistic modeling:\n\n---\n\n### 📊 Discrete Distributions\n\n#### **Binomial Distribution**  \n\nModels the number of successes in \\(n\\) independent trials with probability \\(p\\).\n\n$$\nP(X = k) = \\binom{n}{k} p^k (1-p)^{n-k}\n$$\n\n**Use Cases**: A/B testing, quality control, medical trials  \n\n---\n\n#### **Poisson Distribution**  \n\nModels the number of events occurring in a fixed interval.\n\n$$\nP(X = k) = \\frac{\\lambda^k e^{-\\lambda}}{k!}\n$$\n\n**Use Cases**: Customer arrivals, system failures, web traffic  \n\n---\n\n### 📈 Continuous Distributions\n\n#### **Gaussian (Normal) Distribution**  \n\nThe cornerstone of probabilistic modeling with symmetric, bell-shaped curves.\n\n$$\nf(x) = \\frac{1}{\\sigma\\sqrt{2\\pi}} \\exp\\left(-\\frac{(x-\\mu)^2}{2\\sigma^2}\\right)\n$$\n\n**Use Cases**: Neural network weights, measurement errors, natural phenomena  \n\n---\n\n#### **Exponential Distribution**  \n\nModels waiting times and survival analysis.\n\n$$\nf(x) = \\lambda e^{-\\lambda x}, \\quad x \\geq 0\n$$\n\n**Use Cases**: System reliability, queueing theory, survival analysis  \n\n---\n\n### 🌐 Multivariate Distributions\n\n#### **Multivariate Gaussian**  \n\nEssential for modeling correlated variables with full covariance structure.\n\n$$\nf(\\mathbf{x}) = \\frac{1}{\\sqrt{(2\\pi)^k|\\boldsymbol{\\Sigma}|}}\n\\exp\\left(-\\frac{1}{2}(\\mathbf{x}-\\boldsymbol{\\mu})^T\\boldsymbol{\\Sigma}^{-1}(\\mathbf{x}-\\boldsymbol{\\mu})\\right)\n$$\n\n**Use Cases**: Dimensionality reduction, portfolio optimization, computer vision  \n\n\n---\n\n## 🧪 Hands-On Examples\n\n### Comprehensive Notebook Collection\n\n| # | Topic | Difficulty | Key Concepts | Notebook |\n|---|-------|------------|--------------|----------|\n| 00 | Univariate Distributions | 🟢 Beginner | Normal, Exponential, Beta distributions | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/00_Univariate_Distributions.ipynb) |\n| 01 | Multivariate Distributions | 🟡 Intermediate | MultivariateNormal, covariance structure | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/01_MultiVariate_Distributions.ipynb) |\n| 02 | Independent Distributions | 🟡 Intermediate | tfd.Independent, batch dimensions | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/02_Independent_Distributions.ipynb) |\n| 03 | Sampling \u0026 Log Probabilities | 🟡 Intermediate | sample(), log_prob(), Monte Carlo | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/03_Sampling%20and%20Log%20Probabilities.ipynb) |\n| 04 | Trainable Distributions | 🟡 Intermediate | tf.Variable parameters, gradient flow | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/04_Trainable_Distributions.ipynb) |\n| 05 | TFP Distributions Summary | 🟢 Reference | Distribution catalog, API reference | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/05_tfp_Distributions_Summary_.ipynb) |\n| 06 | Independent Naive Classifier | 🟡 Intermediate | Feature independence, text classification | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/06_Independent_dist_Naive_Clasif.ipynb) |\n| 07 | Naive Bayes with TFP | 🟡 Intermediate | Bayes' theorem, posterior computation | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/07_Naive_Bayes_Classif_with_TFP.ipynb) |\n| 08 | Multivariate Gaussian Full Covariance | 🔴 Advanced | Full covariance, correlation modeling | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/08_Multivariate_Gaussian_with_full_covariance.ipynb) |\n| 09 | Broadcasting Rules | 🟡 Intermediate | Shape manipulation, batch processing | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/09_Broadcasting_rules.ipynb) |\n| 10 | Naive Bayes \u0026 Logistic Regression | 🟡 Intermediate | Generative vs discriminative models | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](01_The%20TensorFlow_Probability_library/10_Naive_Bayes_%26_logistic_regression.ipynb) |\n| 11 | Probabilistic Layers \u0026 Bayesian NNs | 🔴 Advanced | DenseVariational, weight uncertainty | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](02_Probabilistic_layers_and_Bayesian_Neural_Networks/Probabilistic_layers_and_Bayesian_Neural_Networks.ipynb) |\n| 12 | Bijectors \u0026 Normalizing Flows | 🔴 Advanced | tfp.bijectors, invertible transforms | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](03_Bijectors_and_Normalising_Flows/Bijectors_and_Normalising_Flows.ipynb) |\n| 13 | Variational Autoencoders | 🔴 Advanced | ELBO, reparameterization trick | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](04_Variational_Autoencoders/Variational_Autoencoders.ipynb) |\n| 14 | Probabilistic Generative Models | 🔴 Expert | Complete pipeline, model evaluation | [![Open Notebook](https://img.shields.io/badge/Open-Notebook-blue)](05_Capstone_Project/Probabilistic_generative_models.ipynb) |\n\n---\n\n\n## 📊 Performance Benchmarks\n\n### Training Time Comparison\n\n| Model Type | Dataset | Standard NN | Bayesian NN | VAE | Normalizing Flow |\n|------------|---------|-------------|-------------|-----|------------------|\n| MNIST Classification | 60k samples | 2 min | 8 min | 12 min | 15 min |\n| CIFAR-10 Classification | 50k samples | 15 min | 45 min | 60 min | 90 min |\n| CelebA Generation | 200k samples | N/A | N/A | 120 min | 180 min |\n\n\u003e*Benchmarks on NVIDIA RTX 3080 GPU*\n\n### Memory Usage\n\nProbabilistic models typically require **2-4x more memory** than standard models due to:\n- Parameter uncertainty representation\n- Additional forward/backward passes\n- Sampling operations during training\n\n---\n\n## 🎯 TensorFlow Probability vs TensorFlow Core\n\n| **Aspect** | **TensorFlow Probability (TFP)** | **TensorFlow Core (TF)** |\n|------------|-----------------------------------|--------------------------|\n| **Primary Focus** | Probabilistic modeling, uncertainty quantification | Deterministic neural networks, optimization |\n| **Model Output** | Distributions with uncertainty bounds | Point estimates |\n| **Key Strengths** | Bayesian inference, generative modeling | Fast training, established workflows |\n| **Learning Curve** | Steeper (requires probability theory) | Gentler (standard ML concepts) |\n| **Memory Usage** | Higher (parameter distributions) | Lower (point parameters) |\n| **Training Time** | Slower (sampling, variational inference) | Faster (direct optimization) |\n| **Interpretability** | Higher (uncertainty quantification) | Lower (black box predictions) |\n| **Best Use Cases** | Critical decisions, small data, research | Large datasets, production systems |\n\n---\n\n## 🤝 Contributing\n\nWe welcome contributions from the community! Here's how you can help:\n\n### Contribution Process\n1. **Fork** the repository\n2. **Create** a feature branch (`git checkout -b feature/amazing-feature`)\n3. **Commit** your changes (`git commit -m 'Add amazing feature'`)\n4. **Push** to the branch (`git push origin feature/amazing-feature`)\n5. **Open** a Pull Request\n\n---\n\n## 🌟 Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow\u0026type=Date)](https://star-history.com/#mohd-faizy/Probabilistic-Deep-Learning-with-TensorFlow\u0026Date)\n\n---\n\n## 📚 Additional Resources\n\n### Reference Materials\n- [Probability Cheatsheet A](CheatSheet/01_Probability_Cheatsheet_a.pdf)\n- [Probability Cheatsheet B](CheatSheet/02_Probability_Cheatsheet_b.pdf)\n- [TensorFlow Probability Official Guide](https://www.tensorflow.org/probability)\n\n### Research Papers\n\n#### Foundational Papers\n- [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114) - Kingma \u0026 Welling (2013)\n- [Stochastic Backpropagation and Approximate Inference in Deep Generative Models](https://arxiv.org/abs/1401.4082) - Rezende et al. (2014)\n- [Weight Uncertainty in Neural Networks](https://arxiv.org/abs/1505.05424) - Blundell et al. (2015)\n- [Variational Inference: A Review for Statisticians](https://arxiv.org/abs/1601.00670) - Blei et al. (2017)\n- [Probabilistic Machine Learning and Artificial Intelligence](https://www.nature.com/articles/nature14541) - Ghahramani (2015)\n\n#### Normalizing Flows \u0026 Bijectors\n- [Normalizing Flows for Probabilistic Modeling and Inference](https://arxiv.org/abs/1912.02762) - Papamakarios et al. (2019)\n- [Density estimation using Real NVP](https://arxiv.org/abs/1605.08803) - Dinh et al. (2016)\n- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://arxiv.org/abs/1807.03039) - Kingma \u0026 Dhariwal (2018)\n\n#### Bayesian Neural Networks\n- [Practical Variational Inference for Neural Networks](https://papers.nips.cc/paper/2011/hash/7eb3c8be3d411e8ebfab2f32016d5ee5-Abstract.html) - Graves (2011)\n- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://arxiv.org/abs/1703.04977) - Kendall \u0026 Gal (2017)\n- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://arxiv.org/abs/1612.01474) - Lakshminarayanan et al. (2017)\n\n#### Variational Inference \u0026 MCMC\n- [Black Box Variational Inference](https://arxiv.org/abs/1401.0118) - Ranganath et al. (2014)\n- [Automatic Differentiation Variational Inference](https://arxiv.org/abs/1603.00788) - Kucukelbir et al. (2017)\n- [The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo](https://arxiv.org/abs/1111.4246) - Hoffman \u0026 Gelman (2014)\n\n#### TensorFlow Probability Specific\n- [TensorFlow Distributions](https://arxiv.org/abs/1711.10604) - Dillon et al. (2017)\n- [Probabilistic Programming and Bayesian Methods for Hackers](https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers) - Davidson-Pilon (2015)\n\n#### Applications \u0026 Case Studies\n- [Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection](https://arxiv.org/abs/2002.05796) - Chang et al. (2020)\n- [Predictive Uncertainty Estimation via Prior Networks](https://arxiv.org/abs/1909.00218) - Malinin \u0026 Gales (2018)\n\n\n---\n\n## ⚖️ License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details\n\n---\n\n## 🔗 Connect with me\n\n\u003cdiv align=\"center\"\u003e\n\n[![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge\u0026logo=twitter\u0026logoColor=white)](https://twitter.com/F4izy)\n[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge\u0026logo=linkedin\u0026logoColor=white)](https://www.linkedin.com/in/mohd-faizy/)\n[![Stack Exchange](https://img.shields.io/badge/Stack_Exchange-1E5397?style=for-the-badge\u0026logo=stack-exchange\u0026logoColor=white)](https://ai.stackexchange.com/users/36737/faizy)\n[![GitHub](https://img.shields.io/badge/GitHub-100000?style=for-the-badge\u0026logo=github\u0026logoColor=white)](https://github.com/mohd-faizy)\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohd-faizy%2Fprobabilistic-deep-learning-with-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmohd-faizy%2Fprobabilistic-deep-learning-with-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohd-faizy%2Fprobabilistic-deep-learning-with-tensorflow/lists"}