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/Deep Learning. 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.
- 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 2.9 Probability, “R”/Python and open source software library for high performance numerical computation.
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 firstname.lastname@example.org.
Note: There is a $25 fee to access the AX Account for this course (access to execute scripts in a persistent environment).
Course Number: CSE-41305
Credit: 3.00 unit(s)
Related Certificate Programs: Machine Learning Methods, Selected Topics in Artificial Intelligence
+ Expand All
3/28/2023 - 5/27/2023
This course is entirely web-based and to be completed asynchronously between the published course start and end dates. Synchronous attendance is NOT required.
You will have access to your online course on the published start date OR 1 business day after your enrollment is confirmed if you enroll on or after the published start date.
Bilyana Aleksic is senior staff hardware engineer with more than 20 years of experience in complex chip SOC development. She received her master's in control systems from Faculty of Electrical Engineering University of Belgrade, former Yugoslavia, and was an honored student of Mathematical Gymnasium, winning many world Mathematical Olympiad Competitions. Aleksic spent 15 years at Canadian tech company ATI Technologies where she worked on implementation of graphics CPU chips. After she moved to California she spent 7 years in mobile chips implementation and verification methodology development. During the past year she shifted her focus to machine learning for medical applications.
No information available at this time.
No refunds after: 4/3/2023.
3/28/2023 - 5/27/2023
You will have access to your course materials on the published start date OR 1 business day after your enrollment is confirmed if you enroll on or after the published start date.
There are no sections of this course currently scheduled. Please contact the Science & Technology department at 858-534-3229 or email@example.com for information about when this course will be offered again.