Practical Deep Learning in Theano and TensorFlow
103 Enrolled
3 Hours
Deal Price$29.00
Suggested Price
$120.00
You save 75%
Practical Deep Learning in Theano and TensorFlow
$29.00$120.0075% OFF
23 Lessons (3h)
- Outline, the MNIST dataset, and Linear (Logistic Regression) BenchmarkOutline - what did you learn previously, and what will you learn in this course?2:35Where to get the MNIST dataset and Establishing a Linear Benchmark4:31
- Gradient Descent: Full vs Batch vs StochasticWhat are full, batch, and stochastic gradient descent?2:45Full vs Batch vs Stochastic Gradient Descent in code5:38
- Momentum and adaptive learning ratesMomentum1:56Code for training a neural network using momentum6:41Variable and adaptive learning rates3:13Constant learning rate vs. RMSProp in Code4:05Hyperparameter Optimization: Cross-validation, Grid Search, and Random Search3:19
- TheanoTheano Basics: Variables, Functions, Expressions, Optimization7:47Building a neural network in Theano9:17
- TensorFlowTensorFlow Basics: Variables, Functions, Expressions, Optimization7:27Building a neural network in TensorFlow9:43
- Modern Regularization TechniquesDropout Regularization11:38
- GPU Speedup and HomeworkSetting up a GPU Instance on Amazon Web Services7:06Exercises and Concepts Still to be Covered2:13
- Project: Facial Expression RecognitionFacial Expression Recognition Problem Description12:21The class imbalance problem6:01Utilities walkthrough5:45Class-Based ANN in Theano19:09Class-Based ANN in TensorFlow15:28
- AppendixManually Choosing Learning Rate and Regularization Penalty4:08How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow17:22
Practical Deep Learning in Theano and TensorFlow
$29.00$120.0075% OFF
DescriptionInstructorImportant DetailsRelated Products
Build & Understand Neural Networks Using Two of the Most Popular Deep Learning Techniques
LP
Lazy ProgrammerThe Lazy Programmer is a data scientist, big data engineer, and full stack software engineer. For his master's thesis he worked on brain-computer interfaces using machine learning. These assist non-verbal and non-mobile persons to communicate with their family and caregivers.
He has worked in online advertising and digital media as both a data scientist and big data engineer, and built various high-throughput web services around said data. He has created new big data pipelines using Hadoop/Pig/MapReduce, and created machine learning models to predict click-through rate, news feed recommender systems using linear regression, Bayesian Bandits, and collaborative filtering and validated the results using A/B testing.
He has taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Humber College, and The New School.
Multiple businesses have benefitted from his web programming expertise. He does all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies he has used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases he has used MySQL, Postgres, Redis, MongoDB, and more.
Terms
- Unredeemed licenses can be returned for store credit within 30 days of purchase. Once your license is redeemed, all sales are final.
Your Cart
Your cart is empty. Continue Shopping!
Processing order...


