Building Classification Models with TensorFlow

By Janani Ravi
This course covers the finer points of building such models as well the logistic regression, nearest-neighbor methods, and metrics for evaluating classifiers such as accuracy, precision, and recall.
Play course overview
Course info
Rating
(27)
Level
Intermediate
Updated
Oct 19, 2017
Duration
3h 16m
Table of contents
Course Overview
Course Overview 2m
Overview of Classification Models
Prerequisites and Software Needed for This Course 3m Classification and Classifiers 5m Using Accuracy to Evaluate Models 4m Using Precision and Recall to Evaluate Models 2m The Precision/Recall Tradeoff 4m The Precision-Recall Tradeoff 3m Binary, Multilabel, Multiclass, and Multioutput Classifiers 4m
Simple Classification Models in TensorFlow
Representing Images as Tensors 4m The K-nearest Neighbors Algorithm 3m Distance Measures 1m Demo: Environment and Package Setup 2m Demo: Image Classification Using K-nearest Neighbors 10m The Intuition Behind Logistic Regression 5m Logistic Regression for Prediction 2m Cross-entropy as a Cost Function 2m Demo: Exploring the Census Dataset 3m Feature Engineering with Bucketized and Crossed Columns 3m Working with Estimators in TensorFlow 4m Demo: Income Prediction Using Logistic Regression 7m
Convolutional Neural Networks for Classification in TensorFlow
Neurons and Neural Networks 6m Understanding How Convolution Works 6m Zero Padding and Stride Size 4m Introducing Convolutional Neural Networks 3m Convolutional Layers and Feature Maps 6m Pooling Layers 3m Architecture of CNNs 5m Demo: Image Classification Using CNNs (MNIST Dataset) 10m Demo: Exploring the CIFAR-10 Dataset 4m Demo: Image Classification Using CNNs (CIFAR-10 Dataset) 7m
Recurrent Neural Networks for Classification in TensorFlow
Why Is the Past Important? 4m Understaning the Recurrent Neuron 4m Training Using Back Propogation 5m Demo: Classifying Images Using RNNs (MNIST Dataset) 4m Dealing with Vanishing and Exploding Gradients 6m The LSTM Memory Cell 5m Word Vector Encodings 7m Demo: Exploring the DBPedia Dataset for Text Classification 7m Demo: Text Classification Using RNNs 8m Summary and Next Steps for Learning 1m
Description
Course info
Rating
(27)
Level
Intermediate
Updated
Oct 19, 2017
Duration
3h 16m
Description

TensorFlow is a great way to implement powerful classification models such as Convolutional Neural Networks and Recurrent Neural Networks. In this course, Building Classification Models with TensorFlow, you'll learn a variety of different machine learning techniques to build classification models. First, you'll begin by covering metrics, such as accuracy, precision, and recall that can be used to evaluate classification models and determine which metric is the right one for your use case. Next, you'll delve into more traditional machine learning techniques such as logistic regression and the k-nearest neighbor methods for classification. Finally, you'll discover how to implement more powerful classification models such as Convolutional Neural Networks and Recurrent Neural Networks. By the end of this course, you'll have a better understanding of how to build classification models with TensorFlow.

About the author
Janani Ravi
About the author

A problem solver at heart, Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework.

More from the author
Building Features from Image Data
Advanced
2h 10m
Aug 13, 2019
Designing a Machine Learning Model
Intermediate
3h 24m
Aug 13, 2019
Building Features from Nominal Data
Intermediate
2h 39m
Aug 12, 2019
More courses by Janani Ravi
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi. My name is Janani Ravi, and welcome to this course on Building Classification Models in TensorFlow. I'll introduce myself. I have a Masters in electrical engineering from Stanford and have worked at companies such as Microsoft, Google, and Flipkart. At Google, I was one of the first engineers working on a real-time collaborative editing in Google Docs, and I hold four patents for its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high-quality video content. This course covers the fine points of classification models. We'll start by understanding how classification works and the metrics to use to evaluate classifiers, such as accuracy, position, and recall. We start off with basic machine learning models for classification, such as the logistic regression and nearest neighbor methods and implement them using TensorFlow's Python APIs. TensorFlow has a great library to implement powerful classification models using Convolutional Neural Networks and Recurrent Neural Networks. Convolutional Neural Networks, or CNNs, are a class of deep feet forward artificial neural network that have successfully been applied to analyzing visual imagery. CNNs are widely used in image and video recognition. Recurrent Neural Networks, or RNNs, are a versatile and powerful form of neural network fast gaining popularity in applications that need to consider context. RNNs are ideal for considering sequences of data, frames in a movie, sentences in a paragraph, or stock returns in a period. This course will cover all these techniques in detail.

You're the smartest person in the room

PROVE IT

Your team won't just close the skills gap

THEY'LL HURDLE IT