DeepLearningAI

Adam Optimization Algorithm (C2W2L08)

Hyperparameter Tuning in Practice (C2W3L03)

Normalizing Activations in a Network (C2W3L04)

Gradient Descent With Momentum (C2W2L06)

Bias Correction of Exponentially Weighted Averages (C2W2L05)

Understanding Exponentially Weighted Averages (C2W2L04)

Tuning Process (C2W3L01)

Exponentially Weighted Averages (C2W2L03)

The Problem of Local Optima (C2W3L10)

Mini Batch Gradient Descent (C2W2L01)

Understanding Mini-Batch Gradient Dexcent (C2W2L02)

Learning Rate Decay (C2W2L09)

Gradient Checking Implementation Notes (C2W1L14)

Gradient Checking (C2W1L13)

Using an Appropriate Scale (C2W3L02)

deeplearning.ai's Heroes of Deep Learning: Andrej Karpathy

deeplearning.ai's Heroes of Deep Learning: Ian Goodfellow

deeplearning.ai's Heroes of Deep Learning: Pieter Abbeel

Deep reinforcement learning is evolving from a field reliant on manual domain expertise to one capable of autonomous, generalized problem-solving. While deep supervised learning successfully automated feature representation, reinforcement learning still faces significant hurdles regarding exploration, credit assignment...

deeplearning.ai's Heroes of Deep Learning: Yoshua Bengio

deeplearning.ai's Heroes of Deep Learning: Ruslan Salakhutdinov

Deep learning has evolved from a reliance on restricted Boltzmann machines for pre-training to the dominance of standard backpropagation, driven by significant advancements in computational power. Russ, a research director at Apple and professor at Carnegie Mellon, explains that while early deep learning models require...