Skip to content

Latest commit

 

History

History
73 lines (66 loc) · 1.96 KB

keywords.md

File metadata and controls

73 lines (66 loc) · 1.96 KB

TensorFlow in Practice Specialization

https://www.coursera.org/specializations/tensorflow-in-practice?#courses

Keywords

1. Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning:

  • machine learning;
  • neural network;
  • loss function;
  • optimizers;
  • training;
  • predict;
  • convergence;
  • epochs;
  • neurons;
  • convolutional neural network;
  • filter;
  • pooling;
  • confinet (ConvNet);
  • image generator (TF);
  • learning rate;
  • data augmentation;
  • tensorFlow's Image Generation lib;
  • transfer learning;
  • inception network;
  • multicast learning;
  • image data generator;
  • image augmentation;
  • Inception model;
  • Fine-Tuning;
  • Feature Extraction;
  • dropouts;
  • multi-class classifiers;
  • natural language processing;
  • tokens (keras Tokenizer);
  • hyperparameter;
  • encode sentences;
  • embeddings;
  • word embeddings;
  • TensorFlow Data Services or TFTS;
  • eager_execution;
  • Pre-tokenized;
  • recurrent neural networks;
  • embedding dimension;
  • Long short-term memory (LSTM);
  • Cell State;
  • Gated Recurrent Units (GRU);
  • sequence models
  • sunspot activity
  • dense model
  • stateless vs stateful
  • imputation (project back into the past to see how we got to where we are now or fill missing data)
  • trend - an overall direction for data regardless of direction
  • seasonality - a regular change in shape of the data
  • autocorrelation - data that follows a predictable shape, even if the scale if diff
  • noise - unpredictable changes in time series data;
  • non-stationary time series - one that has a disruptive event breaking trend and seasonality
  • naive forecasting
  • fixed partitioning
  • roll-forward partitioning
  • training period / validation period / test period
  • Univariate time series
  • mse - square the errors and then calculate their mean.
  • rmse - root means squared error
  • mae - mean absolute error
  • mape - mean absolute percentage error (this gives an idea of the size of the errors compared to the values)
  • moving average
  • differencing