Search "+Peter Norvig +Automated machine learning +Class imbalance problem +Travelling salesman problem -Probability, Paradox, and the Reasonable Person Principle +Cross validation +Cluster analysis +Machine learning +Machine learning for healthcare -Data clustering +Jupyter/notebook +Artemy Kolchinsky +Ulrike von Luxburg +Gradient descent -Neuron"

Positive matches

• 0.112 + - Class imbalance
• 0.028 + - Recommender system
• 0.024 + - IPython notebook
• 0.021 + - Poker
• 0.014 + - IPython
• 0.014 + - Jupyter
• 0.013 + - Learning
• 0.013 + - Privacy and Deanonymization
• 0.012 + - scikit-learn
• 0.011 + - Boosting (machine learning)
• 0.009 + - Deep learning
• 0.009 + - Data science
• 0.008 + - Regular expression
• 0.008 + - Regex
• 0.008 + - SSH tunneling
• 0.008 + - Future of work
• 0.007 + - Paradox
• 0.006 + - Artificial neural network
• 0.006 + - Tom M. MItchell
• 0.006 + - Training dataset

Negative matches

• 0.031 + - Neural network
• 0.001 + - Gender bias
• 0.001 + - sense2vec
• 0.001 + - Paper/Levy2014a
• 0.001 + - GloVe
• 0.001 + - Clinical concept embedding
• 0.001 + - Long short-term memory
• 0.001 + - Paper/Perozzi2014
• 0.001 + - Google
• 0.001 + - Chris McCormick
• 0.001 + - Attention (Deep learning)
• 0.001 + - Wolfgang Maass
• 0.000 + - Paper/Hochreiter1997
• 0.000 + - Paper/Bahdanau2015
• 0.000 + - Rami Al-Rfou
• 0.000 + - Ivo Danihelka
• 0.000 + - KoNLPy
• 0.000 + - Sentiment analysis
• 0.000 + - Topic modeling
• 0.000 + - Paper