We’re in a day and age where machines are doing more and more for us. They’re even using artificial intelligence to help us learn. The Deep Learning and Artificial Intelligence Introductory Bundle will get you caught up on all the latest technology in this regard. You’ll learn about linear and logistic regression and deep learning in Python as well as practical deep learning in Theano and TensorFlow.
The following four courses are included in this great bundle.
Deep Learning Prerequisites: Linear Regression in Python – Make more accurate predictions and step into deep learning using probability
- Twenty lectures and two hours of content
- Prove Moore’s Law using a 1-D linear regression
- Create a machine learning model that will learn from multiple inputs
- Predict a patient’s systolic blood pressure using their age and weight by applying multi-dimensional linear regression
- Go over generalization, overfitting, and train test splits
Deep Learning Prerequisites: Logistic Regression in Python – Get introduced to the building blocks of neural networks.
- Thirty-one lectures and three hours of content
- Learn to code your own logistic regression module in Python
- Learn while working on a course project that predicts user actions from user data on a website
- Utilize facial expression recognition using deep learning
Discover how to make data-driven decisions
Data Science: Deep Learning in Python – Discover how to build artificial neural networks like those that keep Google so knowledgeable.
- Thirty-seven lectures and four hours of content
- Use the softmax function to extend the binary classification model in multiple classes
- Code the important training method, backpropagation, in Numpy
- Put a neural network in play using Google’s TensorFlow library
- Use a neural network and user data to predict user actions on a website
- Use deep learning for facial expression recognition
- Discover the newest developments in neural networks
Data Science: Practical Deep Learning in Theano and TensorFlow – Discover and create neural networks with two of the most popular deep learning techniques.
- Twenty-three lectures and three hours of programming
- Learn batch and stochastic gradient descent which allow you to train on a small sample of data at each iteration, speeding up training time immensely
- Find out how momentum can take you through local minima
- Discover adaptive learning rate techniques such as AdaGrad and RMSprop
- Go over dropout regularization and other modern neural network techniques
- Learn the variables and expressions of TensorFlor and Theano
- Set up a GPU instance on AWS and compare the speeds of CPU and GPU for training a deep neural network
- Compare MNIST dataset and known benchmarks
Pick up this great bundle for 91% off.