Courses from 1000+ universities
AI got cheap enough that Duolingo’s most expensive plan may not survive it. I read the earnings call transcript and opened the app to see what is actually changing for learners.
600 Free Google Certifications
Computer Science
Artificial Intelligence
Data Science
Intelligenza Artificiale
The Bible's Prehistory, Purpose, and Political Future
Education for All: Disability, Diversity and Inclusion
Organize and share your learning with Class Central Lists.
View our Lists Showcase
Learn how the praudio Python library batch-processes entire audio datasets through configurable transforms and preprocessors in a single command.
Learn to standardize variable-length audio by cutting waveforms and applying right-side zero padding in a PyTorch dataset.
Extract Mel spectrograms from audio with Torchaudio, including resampling signals and mixing them down to mono in a PyTorch dataset.
Build and train a feed-forward neural network in PyTorch, using MNIST digit classification to explore datasets, data loaders, and training loops.
Strategies for asking thoughtful, well-contextualized questions that improve workplace communication and increase the likelihood of receiving useful answers.
Learn how Infinite Remixer uses beat tracking, chromograms, MFCCs, and nearest-neighbor search to create automatic song remixes.
Use a trained variational autoencoder to generate sound-digit spectrograms and convert them into audio.
Build a Python audio preprocessing pipeline that batches files, extracts log spectrograms, pads data, and normalizes features for AI applications.
Implement a Variational Autoencoder in Python and Keras, from modifying the encoder bottleneck and loss to training and visualising its latent space.
Explore how generative music tools are changing listening, music creation, and soundtrack production for media.
Seven AI music project ideas—from genre classification and recommendation to accompaniment and noise cancellation—for building an AI engineering portfolio.
Learn how multivariate normal distributions transform vanilla autoencoders into variational autoencoders with smoother latent spaces for generative tasks.
Generate handwritten-digit images with an autoencoder, visualize its latent representation, and examine why variational autoencoders improve generative results.
Build and train an autoencoder in Python with Keras and TensorFlow using encoder-decoder architecture and the MNIST dataset.
Implement an autoencoder’s encoder in Python and Keras, adding convolutional layers and a bottleneck with TensorFlow.
Get personalized course recommendations, track subjects and courses with reminders, and more.