I’ve developed several courses for Kaggle Learn:

Intro to Deep Learning

Description: Use TensorFlow and Keras to build and train neural networks for structured data.

  1. A Single Neuron - Learn about linear units, the building blocks of deep learning.
  2. Deep Neural Networks - Add hidden layers to your network to uncover complex relationships.
  3. Stochastic Gradient Descent - Use Keras and Tensorflow to train your first neural network.
  4. Overfitting and Underfitting - Improve performance with extra capacity or early stopping.
  5. Dropout and Batch Normalization - Add these special layers to prevent overfitting and stabilize training.
  6. Binary Classification - Apply deep learning to another common task.
  7. (Bonus) Detecting the Higgs Boson with TPUs

Computer Vision

Description: Build convolutional neural networks with TensorFlow and Keras.

  1. The Convolutional Classifier - Create your first computer vision model with Keras.
  2. Convolution and ReLU - Discover how convnets create features with convolutional layers.
  3. Maximum Pooling - Learn more about feature extraction with maximum pooling.
  4. The Sliding Window - Explore two important parameters: stride and padding.
  5. Custom Convnets - Design your own convnet.
  6. Data Augmentation - Boost performance by creating extra training data.
  7. (Bonus) Join the Petals to the Metal Competition

Feature Engineering

Description: Better features make better models. Discover how to get the most out of your data.

  1. What is Feature Engineering - Learn the steps and principles of creating better features.
  2. Mutual Information - Locate the features with the most potential.
  3. Creating Features - Transform features with Pandas.
  4. Clustering with K-Means - Untangle complex spatial relationships with cluster labels.
  5. Principal Component Analysis - Discover new features by analyzing variation.
  6. Target Encoding - Boost any categorical feature with this powerful technique.
  7. (Bonus) Feature Engineering for the House Prices Competition

Time Series

Description: Apply machine learning to real-world forecasting tasks.

  1. Linear Regression with Time Series - Use two features unique to time series: lags and time steps.
  2. Trend - Model long-term changes with moving averages and the time dummy.
  3. Seasonality - Create indicators and Fourier features to capture period change.
  4. Time Series as Features - Predict the future from the past with a lag embedding.
  5. Hybrid Models - Combine the strengths of two forecasters with this powerful technique.
  6. Forecasting with Machine Learning - Apply ML to any forecasting task with these four strategies.

Other Work

I’ve also completed some shorter projects.