Add requirements.txt for BNN notebook

Author: krasserm

bayesian-neural-networks/bayesian_neural_networks.ipynb

@@ -6,7 +6,7 @@
  "source": [
  "# Variational inference in Bayesian neural networks\n",
  "\n",
- "This article demonstrates how to implement and train a Bayesian neural network with Keras following the approach described in [Weight Uncertainty in Neural Networks](https://arxiv.org/abs/1505.05424) (*Bayes by Backprop*). The implementation is kept simple for illustration purposes and uses Keras 2.2.4 and Tensorflow 1.12.0. For more advanced implementations of Bayesian methods for neural networks consider using [Tensorflow Probability](https://www.tensorflow.org/probability), for example.\n",
+ "This article demonstrates how to implement and train a Bayesian neural network with Keras following the approach described in [Weight Uncertainty in Neural Networks](https://arxiv.org/abs/1505.05424) (*Bayes by Backprop*). The implementation is kept simple for illustration purposes and uses Keras 2.2.4 and Tensorflow 1.12.0 (see also [requirements.txt](requirements.txt)). For more advanced implementations of Bayesian methods for neural networks consider using [Tensorflow Probability](https://www.tensorflow.org/probability), for example.\n",
  "\n",
  "Bayesian neural networks differ from plain neural networks in that their weights are assigned a probability distribution instead of a single value or point estimate. These probability distributions describe the uncertainty in weights and can be used to estimate uncertainty in predictions. Training a Bayesian neural network via variational inference learns the parameters of these distributions instead of the weights directly.\n",
  "\n",
@@ -426,7 +426,7 @@
  "name": "python",
  "nbconvert_exporter": "python",
  "pygments_lexer": "ipython3",
- "version": "3.6.8"
+ "version": "3.6.12"
  }
  },
  "nbformat": 4,

bayesian-neural-networks/requirements.txt

@@ -0,0 +1,6 @@
+# Dependencies for bayesian_neural_networks.ipynb
+keras==2.2.4
+tensorflow==1.12
+tensorflow_probability==0.5.0
+matplotlib==3.3.2
+tqdm==4.50.2