PTCA PyTorch Certified Associate — Exam Overview
Quick Facts
The PyTorch Certified Associate (PTCA) is a beginner-level Linux Foundation certification validating foundational PyTorch and AI model development skills for engineering and research roles. The exam is multiple-choice, lasts 120 minutes, and costs USD 250 for the exam only. There are no prerequisites; it is designed for early-stage practitioners with some Python and machine learning experience. The certification is valid for 2 years, with 12-month exam eligibility and one retake included.
Who this exam is for
Early-stage practitioners with some Python and machine learning experience who are beginning to use PyTorch in AI and machine learning roles.
Exam Domains
PyTorch Fundamentals — 38%
Covers PyTorch core concepts and tensors, including creation, shapes, dtypes, reshaping, broadcasting, and in-place operations, plus autograd with requires_grad, backward, and .grad. It also addresses training, testing, and using models with the training loop, eval and train modes, no_grad, saving and loading state dicts, and device basics across CPU, CUDA, and MPS.
Model Development — 20%
Covers PyTorch neural network building blocks through nn.Module, including __init__ and forward, and layers such as Linear, Conv2d, Embedding, pooling, and recurrent modules. It also addresses activations, dropout, and batch normalization, parameter inspection and freezing, Sequential containers, and classifier heads with logits and losses.
Performance & Optimization — 26%
Covers precision and execution optimization including mixed precision with autocast and GradScaler, torch.compile, channels-last, TF32, pruning, and gradient checkpointing. It also addresses performance measurement with profiling, throughput benchmarking, and CUDA synchronization, and distributed training with DistributedDataParallel, DistributedSampler, and FSDP.
Data Handling — 16%
Covers datasets and the Dataset protocol with __len__ and __getitem__, DataLoaders for batching, shuffling, workers, and collation, and transforms including ToTensor, Normalize, and training-only augmentation. It also addresses training data practices such as train validation and test splits, padding variable-length sequences, and handling imbalanced data with weighted sampling.
Preparing for PTCA
Work through the practice questions in study mode first, read every explanation, then switch to timed practice. Weight your revision by the domain weightings above and revisit the topics you score lowest on until your practice scores are consistent.
Write Your Review on PTCA PyTorch Certified Associate
PTCA Customer Reviews
No reviews yet
Be the first to share your experience with this exam.