Deep Learning Specialization

ML
Deep Learning
Neural Nets
CNN
ResNet
RNN
GRU
LSTM
Transformers
Andrew Ng’s five-course deep learning specialization — neural networks from scratch, CNNs and ResNets for vision, RNNs and transformers for sequences.
Published

November 13, 2022

Download certificate (PDF) Verify

Skills covered

A 5-course specialization from DeepLearning.AI, taught by Andrew Ng, Kian Katanforoosh, and Younes Bensouda Mourri.

  • Course 1 — Neural Networks and Deep Learning: foundations of DL, vectorised forward/backward propagation, building NNs from scratch in NumPy
  • Course 2 — Improving Deep Neural Networks: practical aspects — initialization, regularization (L2, dropout), batch normalization, optimization (mini-batch, momentum, Adam), hyperparameter tuning
  • Course 3 — Structuring Machine Learning Projects: diagnosing errors, train/dev/test splits, transfer learning, multi-task learning, end-to-end vs pipeline approaches
  • Course 4 — Convolutional Neural Networks: CNN building blocks, classic architectures (LeNet, AlexNet, ResNet, Inception), object detection (YOLO), face recognition, neural style transfer
  • Course 5 — Sequence Models: RNNs, LSTMs, GRUs, language modelling, word embeddings, attention mechanisms, and the basics of Transformer architectures

Issued

DeepLearning.AI — 2022-11-13