Skip to Content
Home /  Courses And Programs / Probability and Statistics for Deep Learning

Probability and Statistics for Deep Learning

Deep Learning is often called “Statistical Learning” and approached by many experts as statistical theory of the problem to find the best model/function approximation from a given collection of data. This course will introduce important concepts of probability theory and statistics which are foundation of todays Machine Learning and especially Generative AI. It will cover many important algorithms and modelling used in supervised and unsupervised learning of neural networks. In addition, the course will introduce tools and underlying mathematical concepts of data interpretation that work with specific models of neural networks. Upon completion of this course you will have acquired the background in probability and statistics necessary for Machine Learning, and have the ability to use TensorFlow to create and train neural networks for specific practical problems. 

Topics Include:

  • Review probability theory basic rules: conditional probability, joint probabilities 
  • Quantify events: Random Variables and becoming familiar with representing big data 
  • Important Distributions for Deep Learning 
  • Statistical Learning: Entropy, KL divergence 
  • Statistical Estimators: MLE and MAP 
  • Logistic Regression and probabilistic models for classification (Kernels 
  • Bayesian concept learning 
  • Supervised Learning Algorithms: Decision Trees and Random Forest 
  • Unsupervised Learning Algorithms: K-Means & Gaussian models (mixture model) 
  • Probabilistic Graphical Model, Markov Model 
  • Utilize TensorFlow-Probability (add on TensorFlow 2.9) for real world example 

Software: TensorFlow 2.11 Probability, Python and open source software library for high performance numerical computation. “R” code accepted a well by the instructor if student prefers it for assignments.  

Course typically offered: Online during our Spring and Fall academic quarters.

Prerequisites: Basic knowledge of Linear Algebra - concept of vectors and matrices. 

Next steps: Upon completion, consider additional coursework in our specialized certificate in Machine Learning Methods to continue learning.

More information: For more information about this course, please contact

Course Number: CSE-41305
Credit: 3.00 unit(s)
Related Certificate Programs: Machine Learning MethodsSelected Topics in Artificial Intelligence

+ Expand All