Unsupervised Deep Learning in Python

Autoencoders, Restricted Boltzmann Machines, Deep Neural Networks, t-SNE and PCA

4.72 (2398 reviews)

Udemy

platform

English

language

Data Science

What you will learn

Understand the theory behind principal components analysis (PCA)

Know why PCA is useful for dimensionality reduction, visualization, de-correlation, and denoising

Derive the PCA algorithm by hand

Write the code for PCA

Understand the theory behind t-SNE

Use t-SNE in code

Understand the limitations of PCA and t-SNE

Understand the theory behind autoencoders

Write an autoencoder in Theano and Tensorflow

Understand how stacked autoencoders are used in deep learning

Write a stacked denoising autoencoder in Theano and Tensorflow

Understand the theory behind restricted Boltzmann machines (RBMs)

Understand why RBMs are hard to train

Understand the contrastive divergence algorithm to train RBMs

Write your own RBM and deep belief network (DBN) in Theano and Tensorflow

Visualize and interpret the features learned by autoencoders and RBMs

Understand important foundations for OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion

Course Gallery

Unsupervised Deep Learning in Python – Screenshot 1 — Screenshot 1 – Unsupervised Deep Learning in Python

Unsupervised Deep Learning in Python – Screenshot 2 — Screenshot 2 – Unsupervised Deep Learning in Python

Unsupervised Deep Learning in Python – Screenshot 3 — Screenshot 3 – Unsupervised Deep Learning in Python

Unsupervised Deep Learning in Python – Screenshot 4 — Screenshot 4 – Unsupervised Deep Learning in Python

Loading charts...

Comidoc Review

Our Verdict

This intermediate-level course provides in-depth instruction on unsupervised deep learning methods with ample Python examples to illustrate the mathematical concepts presented. Its comprehensive coverage of various algorithms and theory-focused approach sets it apart, but may intimidate beginners or those unfamiliar with Theano. Nonetheless, students will walk away with enhanced knowledge and confidence regarding more advanced deep learning training methods.

What We Liked

The course covers advanced topics in unsupervised deep learning with a strong mathematical focus, providing in-depth explanations and justifications for algorithms.
Examples implemented in Python help reinforce concepts, enabling students to immediately apply their learned knowledge.
Course material is comprehensive, exhaustively describing numerous algorithms while offering intuitive explanations.
The instructor encourages an active learning approach, prompting learners to pause the video for self-reflection and hands-on exercises.

Potential Drawbacks

Some students might find explanations too complex or fast-paced, possibly requiring additional review of certain topics.
A lack of beginner-friendly content may intimidate newcomers to unsupervised deep learning.
Code demonstrations could benefit from more annotations and insights into individual steps, enhancing time efficiency.
The course is focused on Theano code examples, with limited TensorFlow content making translation necessary for non-Theano users.