access
Lifetime
content
8.5 Hours
Description
Deep learning isn't just about helping computers learn from data—it's about helping those machines determine what's important in those datasets. This is what allows for Tesla's Model S to drive on its own and for Siri to determine where the best brunch spots are. Using the machine learning workhorse that is TensorFlow, this course will show you how to build deep learning models and explore advanced AI capabilities with neural networks.- Access 62 lectures & 8.5 hours of content 24/7
- Understand the anatomy of a TensorFlow program & basic constructs such as graphs, tensors, and constants
- Create regression models w/ TensorFlow
- Learn how to streamline building & evaluating models w/ TensorFlow's estimator API
- Use deep neural networks to build classification & regression models
Instructor
Loonycorn is comprised of a couple of individuals —Janani Ravi and Vitthal Srinivasan—who have honed their tech expertise at Google and Stanford. The team believes it has distilled the instruction of complicated tech concepts into funny, practical, engaging courses, and is excited to be sharing its content with eager students.Important Details
- Length of time users can access this course: lifetime
- Access options: web
- Certification of completion not included
- Redemption deadline: redeem your code within 30 days of purchase
- Experience level required: intermediate
Terms
- Unredeemed licenses can be returned for store credit within 30 days of purchase. Once your license is redeemed, all sales are final.
Course Outline
- You, This Course and Us
- You, This Course and Us (2:38)
- Source Code and PDFs
- Datasets for all Labs
- Installation
- Install TensorFlow (6:24)
- Install Jupyter Notebook (4:38)
- Running on the GCP vs. Running on your local machine
- Lab: Setting Up A GCP Account (6:59)
- Lab: Using The Cloud Shell (6:01)
- Datalab ~ Jupyter (3:00)
- Lab: Creating And Working On A Datalab Instance (10:29)
- TensorFlow and Machine Learning
- Introducing Machine Learning (8:04)
- Representation Learning (10:27)
- Neural Networks Introduced (7:35)
- Introducing TensorFlow (7:16)
- Running on the GCP vs. Running on your local machine
- Lab: Simple Math Operations (8:46)
- Computation Graph (10:17)
- Tensors (9:02)
- Lab: Tensors (5:03)
- Linear Regression Intro (9:57)
- Placeholders and Variables (8:44)
- Lab: Placeholders (6:36)
- Lab: Variables (7:49)
- Lab: Linear Regression with Made-up Data (4:52)
- Quiz 1: TensorFlow Basics
- Working with Images
- Image Processing (8:05)
- Images As Tensors (8:16)
- Lab: Reading and Working with Images (8:05)
- Lab: Image Transformations (6:37)
- Quiz 2: Images
- K-Nearest-Neighbors with TensorFlow
- Introducing MNIST (4:13)
- K-Nearest Neigbors as Unsupervised Learning (7:42)
- One-hot Notation and L1 Distance (7:31)
- Steps in the K-Nearest-Neighbors Implementation (9:32)
- Lab: K-Nearest-Neighbors (14:14)
- Quiz 3: MNIST with K-Nearest Neighbors
- Linear Regression with a Single Neuron
- Learning Algorithm (10:58)
- Individual Neuron (9:52)
- Learning Regression (7:51)
- Learning XOR (10:26)
- XOR Trained (11:11)
- Linear Regression in TensorFlow
- Lab: Access Data from Yahoo Finance (2:49)
- Non TensorFlow Regression (8:05)
- Lab: Linear Regression - Setting Up a Baseline (11:18)
- Gradient Descent (9:56)
- Lab: Linear Regression (14:42)
- Lab: Multiple Regression in TensorFlow (9:15)
- Quiz 4: Linear Regression
- Logistic Regression in TensorFlow
- Logistic Regression Introduced (10:16)
- Linear Classification (5:25)
- Lab: Logistic Regression - Setting Up a Baseline (7:33)
- Logit (8:33)
- Softmax (11:55)
- Argmax (12:13)
- Lab: Logistic Regression (16:56)
- Quiz 5: Logistic Regression
- The Estimator API
- Estimators (4:10)
- Lab: Linear Regression using Estimators (7:49)
- Lab: Logistic Regression using Estimators (4:54)
- Quiz 6: Estimators
- Neural Networks and Deep Learning
- Traditional Machine Learning (6:24)
- Deep Learning (9:23)
- Operation of a Single Neuron (8:17)
- The Activation Function (10:41)
- Training a Neural Network: Back Propagation (6:40)
- Lab: Automobile Price Prediction - Exploring the Dataset (11:13)
- Lab: Automobile Price Prediction - Using TensorFlow for Prediction (14:35)
- Hyperparameters (6:27)
- Vanishing and Exploding Gradients (12:10)
- The Bias-Variance Trade-off (8:26)
- Preventing Overfitting (7:36)
- Lab: Iris Flower Classification (12:08)
- Quiz 7: Neural Networks and Deep Learning
access
Lifetime
content
8.5 Hours