Skip to main content

Curriculum

Deep Learning

Deep Learning curriculum

Courses

  1. 1
    Foundations of Machine Learning and Deep LearningLearn how neural networks actually work, write your first training loop in PyTorch, and build a small image classifier you can put in a portfolio. No prior ML experience required. Targeted at early undergraduate / freshman–sophomore students.
  2. 2
    Applied Deep Learning with GPU AccelerationLearn to build, train, and deploy deep learning models in PyTorch, with a real understanding of what happens at the GPU level, from tensors to TensorRT. Targeted at applied undergraduate / junior-senior students.
  3. 3
    Deep Learning Systems, Frameworks, and Inference OptimizationA graduate-level, NVIDIA-aligned career-readiness course for MS, MBA, and PhD-prep students who already know PyTorch and want to understand how deep learning actually runs — from Python down through cuDNN, CUDA, and the GPU. In ~10 hours you'll study framework internals, GPU architecture, quantization, batching, inference optimization, and deployment, then ship a capstone that benchmarks and optimizes a real inference pipeline. Target learner: graduate or advanced senior CS/ECE students pursuing NVIDIA's Deep Learning hiring area (Applications & Algorithms; Frameworks & Libraries).