Deep Learning Specialization

Build, train and apply deep neural networks with TensorFlow and PyTorch, for images, sequences and decisions.

Learn how neural networks work and build them with TensorFlow and Keras, then make deep networks train well: initialisation, normalisation, optimisers and regularisation. Rebuild your skills in PyTorch, apply convolutional networks to computer vision, and finish with reinforcement learning. Every course is hands-on, with labs and a capstone project your instructors review.

Prepares you for

Deep learning engineer, Computer vision engineer, Machine learning engineer

5 courses in this Specialization

• Introduction to Neural Networks and TensorFlow: Build neural networks from the single neuron up: code a perceptron and backpropagation in NumPy, then train and evaluate feed-forward networks with TensorFlow and Keras. (Intermediate, about 13 hours)
• Training Deep Neural Networks: Diagnose and fix what stops deep networks learning: vanishing and exploding gradients, slow or unstable optimisation, overfitting and badly scaled activations, in TensorFlow and Keras. (Advanced, about 14 hours)
• Deep Learning with PyTorch: Build, train, debug and ship neural networks in PyTorch: tensors and autograd, nn.Module, DataLoaders and the training loop, regularisation, checkpoints and export. (Intermediate, about 15 hours)
• Computer Vision with Convolutional Neural Networks: Understand convolutions from the arithmetic up, build CNNs from LeNet to ResNet in PyTorch, and train, transfer and evaluate them for classification, detection and segmentation. (Intermediate, about 17 hours)
• Reinforcement Learning: From Bandits to Policy Gradients: Learn how agents learn from reward, from bandits and dynamic programming through Monte Carlo, TD learning, SARSA and Q-learning to deep Q-networks and policy gradients in PyTorch. (Advanced, about 16 hours)