Exploring AI Foundations with Wolfram Tools
- Instructor Led
- 7 h 30 min
- Intermediate
- 3 Certifications
Estimated Time: 7 h 30 min
Course Level: Intermediate
Requirements: This course requires basic working knowledge of Wolfram Language.
Certification Levels: CompletionLevel 1Level 2
This three-part course sequence will guide you in using the computational power of Wolfram technologies as a foundation for modern AI systems. The first session in the series shows how to use the latest AI tools within the Wolfram ecosystem–use Wolfram Notebook Assistant, embed LLM conversations into notebooks, access LLM capabilities directly in your Wolfram Language workflows and build custom agents. The second course covers core concepts of classic machine learning like supervised and unsupervised learning as well as the easy-to-use machine learning superfunctions available in Wolfram Language. In the third course, you'll learn about the state-of-the-art Neural Net Framework in Wolfram Language and how to explore the Wolfram Neural Net Repository for prebuilt and pretrained models. Each course is available individually, but the course sequence gives you the convenience of a unified schedule and an invitation to a special office hour session. The series includes these courses: Wolfram Language and LLMs, Introduction to Machine Learning in Wolfram Language and Introduction to Neural Networks in Wolfram Language.
Featured Products & Technologies: Wolfram Language and Wolfram Notebooks (available in Mathematica, Wolfram|One and Wolfram|Alpha Notebook Edition), Neural Net Repository
Outline
- Incorporate AI Tools: Use Wolfram Notebook Assistant and embed chat conversations with LLMs right into the notebook as you explore, shape and develop your multimodal workflows.
- Code with LLM Functionality: Programmatically invoke LLMs using functions like LLMFunction, LLMSynthesize and LLMGraph to utilize the power of generative AI and augment your computational pipelines. Use LLMTool to inject reliability into LLMs by allowing them to call upon results computed with Wolfram Language's expansive set of specialized functions and algorithms.
- Explore Hands-on Examples: Work on easy-to-apply practical examples that integrate the use of systematic computation and knowledge with modern AI systems. Take advantage of fun and functional prompts from the Wolfram Prompt Repository and explore the collection of tools in the LLM Tools Repository.
- Build Your Understanding of Classical Machine Learning: Look beyond transformer models like LLMs to learn about other common types of machine learning. Learn about regression, classification, clustering and anomaly detection. Explore the fundamental concepts of neural networks and deep learning. Build simple networks and use transfer learning with pretrained networks to perform new tasks.
- Use Automated Superfunctions with Ease: Use built-in machine learning "superfunctions" like Classify, Predict, FindClusters and ClusterClassify on your own data for simple, quick but extremely powerful applications of neural nets. Download net models from the Wolfram Neural Net Repository to take advantage of the power of neural networks without the overhead of building and training your own networks from scratch.
- Build Machine Learning Workflows: Get data from different external and built-in sources. Build, train and test models following traditional machine learning workflows, then use built-in metrics to evaluate the performance of models. Quickly deploy a model for use with the help of the Wolfram Cloud.
Schedule
Register NowSign Up for This Course Series
February 24–March 101–3:30pm CST, 7–9:30pm UTC/GMT| Online | FreeYour local time
View all scheduled courses and events
Certifications Available
Completion Certificate
Certify your completion of each course in the sequence by attending the online class and passing the quiz.
Level 1 Certification
This course sequence provides excellent preparation for the neural networks Level 1 certification.
See Details
Level 2 Certification
Submit an independent project to demonstrate your applied expertise in neural networks.
See Details
