Build projects like a text summarizer! Learn object localization, image recognition and structuring data with pandas
What you’ll learn
- Code in 3 programming languages: Java, Python and Swift
Build nodes and data models for linear regression
Use summarizing mechanisms to handle text data
- Test projects on mobile devices
- Examine computational graphs
- Analyze scalars and histograms
- Build neuron functions
- Load, convert, and display image and digit data
- Describe data with statistics
- And much more…
“Excellent! Thank you for all your hard work.” – Mammoth Interactive student Inderpal ⭐ ⭐ ⭐ ⭐ ⭐
Dive into a world of data science and analysis with a wide range of examples including the CIFAR 100 image dataset, Xcode development for Apple, Swift coding, CoreML, image recognition, and structuring data with pandas.
This Mammoth Interactive course was funded by a #1 project on Kickstarter
Learn Android Studio, Java, app development, Pycharm, Python coding, Tensforflow and more with Mammoth Interactive.
Build advanced projects using machine learning including advanced the MNIST database with neuron functions. Build a text summarizer and learn object localization, object recognition and Tensorboard.
Machine learning is a machine’s ability to make decisions or predictions based on previous exposure to data and extensive training. In other words, if a machine (program, app, etc.) improves its prediction accuracy through training then it has “learned”.
Learn How Models Work
Computational graphs consist of a network of connected nodes (often called neurons). Each of these nodes typically has a weight and a bias that helps determine, given an input, which path is the most likely.
There are 4 main components to building a machine learning program: data gathering and formatting, model building, training, and testing and evaluating
Data Gathering and Formatting
You will learn to gather plenty of data for the model to learn from.
All data should be formatted pretty much the same (images same size, same color scheme, etc.) and should be labelled. Also divide data into mutually exclusive training and testing sets.
You will learn to figure out which kind of model scheme works best and what kinds of algorithms work best for the problem you’re trying to solve.
Training, Testing and Evaluating
The model can choose paths through the neural network or computational graph based upon the inputs for a particular run, as well as the weights and biases of neurons in the network.
In supervised learning, we show the model what the correct outputs are for a given set of inputs and the model alters the weights and biases of neurons to minimize the difference between its output and the correct answer.
Enroll Now to Learn with Mammoth Interactive
- Topics involve intermediate math, so familiarity with university-level math is very helpful
Created by Mammoth Interactive, John Bura
Last updated 6/2018
Size: 14.12 GB