This course was created with the
course builder. Create your online course today.
Start now
Create your course
with
Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Introduction to Deep Learning
Course Lectures
001. Welcome to AML Specialization! (2:49)
002. Course Intro (6:02)
003. Linear regression (9:58)
004. Linear classification (10:50)
005. Gradient descent (5:04)
006. Overfitting problem and model validation (6:56)
007. Model regularization (5:20)
008. Stochastic gradient descent (5:40)
009. Gradient descent extensions (9:58)
010. Multilayer perceptron (MLP) (12:36)
011. Chain rule (7:30)
012. Backpropagation (9:01)
013. Efficient MLP implementation (13:08)
014. Other matrix derivatives (5:54)
015. What is TensorFlow (10:54)
016. Our first model in TensorFlow (10:11)
017. What Deep Learning is and is not (8:37)
018. Deep learning as a language (6:59)
019. Motivation for convolutional layers (11:14)
020. Our first CNN architecture (10:59)
021. Training tips and tricks for deep CNNs (14:48)
022. Overview of modern CNN architectures (8:19)
023. Learning new tasks with pre-trained CNNs (5:16)
024. A glimpse of other Computer Vision tasks (8:17)
025. Unsupervised learning what it is and why bother (5:57)
026. Autoencoders 101 (5:34)
027. Autoencoder applications (9:42)
028. Autoencoder applications image generation, data visualization & more (7:19)
029. Natural language processing primer (10:10)
030. Word embeddings (13:21)
031. Generative models 101 (7:31)
032. Generative Adversarial Networks (10:05)
033. Applications of adversarial approach (11:08)
034. Motivation for recurrent layers (7:36)
035. Simple RNN and Backpropagation (8:23)
036. The training of RNNs is not that easy (7:19)
037. Dealing with vanishing and exploding gradients (9:02)
038. Modern RNNs LSTM and GRU (11:30)
039. Practical use cases for RNNs (13:17)
009. Gradient descent extensions
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock