Most “intro to AI” material assumes you already code and still remember your linear algebra. This program refuses that assumption: it teaches the Python and the maths first, then has you build a neural network in PyTorch and finish by pointing a Transformer at a language task. Read it as the runway towards machine learning and deep learning proper, not a destination in itself.
AI Programming with Python
The plumbing AI assumes you already know
Closes the gap most aspiring AI engineers hit first: they can write a little code, but not the programming-and-maths groundwork that machine-learning material takes for granted. It walks from language basics to a working model in PyTorch, with data libraries in between.
What you will learn
- →Read and write Python with confidence, including its core data structures and control flow
- →Shape and chart datasets with NumPy, pandas and Matplotlib
- →Assemble, train and evaluate a neural network in PyTorch from scratch
- →Put a pre-trained Transformer to work on a text task
Curriculum
- 1Introduction to AI Programming
- 2Beginner Python (PCEP™ certification prep)
Aligned to the PCEP entry-level Python certification
- 3NumPy, pandas, Matplotlib
- 4Neural networks
- 5Programming Transformers with PyTorch
Prerequisites
- Basic programming experience
- Elementary algebra and basic calculus
- Basic Git/GitHub
Concepts this course teaches
- Python
Builds Python from the basics as the program's core.
- Neural Networks
First hands-on neural network, built in PyTorch.
- Transformers
Closes with applying pre-trained Transformers.
- Natural Language Processing
Uses pre-trained models for language tasks.
- Machine Learning
An on-ramp toward machine-learning study.
- Deep Learning
Sets up the move into deep learning proper.
FAQ
- I can barely code. Is that enough to start?
- Yes. A little prior coding helps, but the program rebuilds the Python and maths from the bottom up, which is exactly its reason to exist.
- Where does it leave me?
- Ready for the next step rather than job-ready: you will have trained real models, which is the entry ticket to a deep-learning or machine-learning program.
Course facts
- Provider
- Udacity
- Level
- beginner
- Duration
- About 52 hours · Self-paced
- Price
- Subscription: pricing set by Udacity
- Pace
- self-paced
- Credential
- nanodegree
PythonNumPypandasMatplotlibPyTorchNeural networksGradient descentBackpropagation
View course at UdacityAffiliate disclosure: course links are affiliate links; an enrolment through one may pay Getting Digital a commission from the provider, at no extra cost to the learner, and it does not influence how courses are described.