Machine Learning Concepts

  • Tensors: are used to encode the signal for processing, as well as the internal states and parameters of models.
    • Manipulating data through this constrained structure allows to use CPUs and GPUs at near peak performance.
  • Zero shot learning (ZSL): a machine learning process where at the inference time, a learner observes samples from classes, which were not observed during the training process, but it needs to predict the class that they belong to.
  • Experiment Tracking: MLOps task for managing model changes over time to meet the goals over training process.