Autoplay
Autocomplete
Previous Lesson
Complete and Continue
AI: Building Machine Learning Systems From Scratch
Section 1 Welcome
Lecture 1 Welcome (2:30)
Lecture 2 TensorFlow's Main Data Structure (7:16)
Lecture 3 Handling the Computing Workflow (5:20)
Lecture 4 Basic Tensor Methods (8:11)
Lecture 5 Basic Tensor Methods (5:29)
Lecture 6 Reading Information from Disk (3:52)
Section 2 Clustering
Lecture 7 Learning from Data –Unsupervised Learning (2:09)
Lecture 8 Mechanics of k-Means (3:28)
Lecture 9 k-Nearest Neighbor (5:29)
Lecture 10 Project 1 – k-Means Clustering on Synthetic Datasets (3:55)
Lecture 11 Project 2 – Nearest Neighbor on Synthetic Datasets (1:39)
Section 3 Linear Regression
Lecture 12 Univariate Linear Modelling Function (4:50)
Lecture 13 Optimizer Methods in TensorFlow – The Train Module (2:58)
Lecture 14 Univariate Linear Regression (5:01)
Lecture 15 Multivariate Linear Regression (5:05)
Section 4 Logistic Regression
Lecture 16 Logistic Function Predecessor – The Logit Functions (4:00)
Lecture 17 The Logistic Function (5:44)
Lecture 18 Univariate Logistic Regression (6:46)
Lecture 19 Univariate Logistic Regression with keras (2:16)
Section 5 Simple FeedForward Neural Networks
Lecture 20 Preliminary Concepts (7:35)
Lecture 21 First Project – Non-Linear Synthetic Function Regression (2:19)
Lecture 22 Second Project – Modeling Cars Fuel Efficiency with Non-Linear Regression (2:52)
Lecture 23 Third Project – Learning to Classify Wines Multiclass Classification (2:42)
Section 6 Convolutional Neural Networks
Lecture 24 Origin of Convolutional Neural Networks (3:20)
Lecture 25 Applying Convolution in TensorFlow (3:43)
Lecture 26 Subsampling Operation –Pooling (2:46)
Lecture 27 Improving Efficiency – Dropout Operation (2:04)
Lecture 28 Convolutional Type Layer Building Methods (0:52)
Lecture 29 MNIST Digit Classification (3:19)
Lecture 30 Image Classification with the CIFAR10 Dataset (2:14)
Section 7 Recurrent Neural Networks and LSTM
Lecture 31 Recurrent Neural Networks (3:33)
Lecture 32 A Fundamental Component (4:11)
Lecture 33 TensorFlow LSTM Useful Classes and Methods (1:49)
Lecture 34 Univariate Time Series Prediction with Energy Consumption Data (2:22)
Lecture 35 Writing Music a la Bach (7:54)
Section 8 Deep Neural Networks
Lecture 36 Deep Neural Network Definition and Architectures Through Time (2:28)
Lecture 37 Alexnet (3:40)
Lecture 38 Inception V3 (0:51)
Lecture 39 Residual Networks (ResNet) (1:55)
Lecture 40 Painting with Style – VGG Style Transfer (2:58)
Section 9 Outro
Lecture 41 Installing TensorFlow on Windows (2:32)
Lecture 42 Installing TensorFlow on MacOS (2:31)
Working Files
Working Files
Lecture 10 Project 1 – k-Means Clustering on Synthetic Datasets
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock