**3.**In machine learning, a mechanism for bucketing categorical data**6.**The primary algorithm for performing gradient descent on neural networks.**9.**Abbreviation for independently and identically distributed**12.**The more common label in a class-imbalanced dataset.**13.**Applying a constraint to an algorithm to ensure one or more definitions of fairness are satisfied.**18.**A process used, as part of training, to evaluate the quality of a machine learning model using the validation set.**19.**A coefficient for a feature in a linear model, or an edge in a deep network.**20.**A column-oriented data analysis API.**21.**Abbreviation for generative adversarial network

**1.**A post-prediction adjustment, typically to account for prediction bias.**2.**A TensorFlow programming environment in which operations run immediately.**4.**Obtaining an understanding of data by considering samples, measurement, and visualization.**5.**An ensemble approach to finding the decision tree that best fits the training data**7.**state-action value function**8.**Loss function based on the absolute value of the difference between the values that a model is predicting and the actual values of the labels**10.**A metric that your algorithm is trying to optimize.**11.**The recommended format for saving and recovering TensorFlow models.**14.**A statistical way of comparing two (or more) techniques, typically an incumbent against a new rival.**15.**When one number in your model becomes a NaN during training, which causes many or all other numbers in your model to eventually become a NaN.**16.**Q-learning In reinforcement learning, implementing Q-learning by using a table to store the Q-functions**17.**A popular Python machine learning API