Merge pull request #1782 from nd-02110114/fix-outdate-example

competition. Increased competition can help drive down the cost of medicine.

## You Will Learn

* [Part 1: The Basic Tools of the Deep Life Sciences](The_Basic_Tools_of_the_Deep_Life_Sciences.ipynb)

* [Part 2: Learning MNIST Digit Classifiers](mnist.ipynb)

* [Part 3: Introduction to Graph Convolutions](graph_convolutional_networks_for_tox21.ipynb)

* [Part 4: Uncertainty Modeling in Deep Learning](Uncertainty.ipynb)

* [Part 5: Model Interpretability](Explaining_Tox21.ipynb)

* [Part 1: The Basic Tools of the Deep Life Sciences](01_The_Basic_Tools_of_the_Deep_Life_Sciences.ipynb)

* [Part 2: Learning MNIST Digit Classifiers](02_Learning_MNIST_Digit_Classifiers.ipynb)

* [Part 3: Modeling Solubility](03_Modeling_Solubility.ipynb)

* [Part 4: Introduction to Graph Convolutions](04_Introduction_to_Graph_Convolutions.ipynb)

* [Part 5: Putting Multitask Learning to Work](05_Putting_Multitask_Learning_to_Work.ipynb)

* [Part 6: Going Deeper on Molecular Featurizations](06_Going_Deeper_on_Molecular_Featurizations.ipynb)

* [Part 7: Uncertainty in Deep Learning](07_Uncertainty_In_Deep_Learning.ipynb)

* [Part 8: Introduction to Model Interpretability](08_Introduction_to_Model_Interpretability.ipynb)

* [Part 9: Creating a high fidelity model from experimental data](09_Creating_a_high_fidelity_model_from_experimental_data.ipynb)

* [Part 10: Exploring Quantum Chemistry with GDB1k](10_Exploring_Quantum_Chemistry_with_GDB1k.ipynb)

* [Part 11: Learning Unsupervised Embeddings for Molecules](11_Learning_Unsupervised_Embeddings_for_Molecules.ipynb)

* [Part 12: Predicting Ki of Ligands to a Protein](12_Predicting_Ki_of_Ligands_to_a_Protein.ipynb)

* [Part 13: Modeling Protein Ligand Interactions](13_Modeling_Protein_Ligand_Interactions.ipynb)

* [Part 14: Modeling Protein Ligand Interactions With Atomic Convolutions](14_Modeling_Protein_Ligand_Interactions_With_Atomic_Convolutions.ipynb)

* [Part 15: Synthetic Feasibility Scoring](15_Synthetic_Feasibility_Scoring.ipynb)

* [Part 16: Conditional Generative Adversarial Networks](16_Conditional_Generative_Adversarial_Networks.ipynb)

* [Part 17: Training a Generative Adversarial Network on MNIST](17_Training_a_Generative_Adversarial_Network_on_MNIST.ipynb)

* [Part 18: Using Reinforcement Learning to Play Pong](18_Using_Reinforcement_Learning_to_Play_Pong.ipynb)

* [Part 19: Large Scale Chemical Screens](19_Large_Scale_Chemical_Screens.ipynb)

* [Part 20: [WIP] ConvertingDeepChem Models to TensorFlow Estimators](WIP_20_Converting_DeepChem_Models_to_TensorFlow_Estimators.ipynb)

* [Part 21: Introduction to Bioinformatics](21_Introduction_to_Bioinformatics.ipynb)