Skip to content
All courses
AdvancedFreePyTorchNeural NetworksCNNsTransfer LearningRNNsNLPGenerative Models

Deep Learning with PyTorch

Build neural networks with modern PyTorch: tensors and autograd, training loops, CNNs and transfer learning, RNNs/LSTMs for sequences, word embeddings and sentiment analysis, then autoencoders and GANs. Train interactively in the browser playground, run the real thing in Colab.

Start course6 modules · 16 lessons

01Neural Networks

What deep learning is, tensors and autograd, the training loop, and your first networks in PyTorch.

  1. What Is Deep Learning?Where deep learning sits inside AI and ML, what a neuron actually computes, and why nonlinear activations give networks their power.
  2. PyTorch & TensorsCreate and reshape tensors, bridge to NumPy, move to the GPU, and let autograd compute derivatives for you.
  3. The Training LoopModel, criterion, optimizer — the three ingredients of training — and the forward-loss-backward-step dance that turns gradients into learning.
  4. Building Networks with nn.ModuleA crash course in Python classes, the anatomy of nn.Module, and an end-to-end MLP classifier — from raw data to accuracy.
  5. Minibatches, Datasets & DataLoadersWhy we train on small batches, how Dataset and DataLoader feed them to the model, and the full modern training recipe with validation, checkpointing, and early stopping.

02Convolutional Neural Networks

Convolutions, pooling, and building CNN image classifiers with data augmentation.

  1. How Convolutions WorkWhy dense layers fail on images, what a convolution actually computes, and the arithmetic of channels, stride, padding, and pooling.
  2. Building a CNN in PyTorchTrain a complete convolutional network on FashionMNIST — transforms, conv-relu-pool blocks with shape bookkeeping, data augmentation, and reading the mistakes.

03Transfer Learning

Famous CNN architectures and how to fine-tune pretrained models on your own data.

  1. Famous CNN ArchitecturesThe ImageNet competition and the ideas it produced — AlexNet's GPUs, VGG's stacked 3×3 kernels, Inception's parallel branches, and ResNet's skip connections.
  2. Transfer Learning in PracticeFreeze a pretrained ResNet, retrain its head on your own images, then fine-tune with a tiny learning rate — and see why this crushes training from scratch.

04Recurrent Neural Networks

Sequence modeling with RNNs, LSTMs, and GRUs — plus bidirectionality and tuning for forecasting.

  1. Recurrent Neural NetworksGive a network memory — the recurrence behind RNNs, unrolling through time, vanishing gradients, and nn.RNN on a next-step prediction task.
  2. LSTM & GRUGated memory cells that beat the vanishing gradient — how LSTM's forget/input/output gates work, GRU's streamlined variant, and both in PyTorch.
  3. Sequence Models in PracticeBidirectional and stacked RNNs, windowing and scaling time series properly, multivariate inputs, and a full LSTM forecasting pipeline with early stopping.

05Natural Language Processing

Word embeddings with Word2Vec and FastText, and an end-to-end sentiment analysis model.

  1. Word Embeddings: Word2Vec & FastTextWhy one-hot vectors fail, how Word2Vec learns meaning from context, and how FastText handles typos and words it has never seen.
  2. Sentiment Analysis End to EndBuild a sentiment classifier three ways — a TF-IDF baseline you can run in the browser, an Embedding + LSTM model in PyTorch, and a modern transformer pipeline.

06Generative Models

Autoencoders for compression and denoising, and GANs that learn to generate images.

  1. AutoencodersTrain a network to compress and reconstruct its own input — and use the bottleneck for dimensionality reduction, denoising, and anomaly detection.
  2. Generative Adversarial NetworksTwo networks locked in a forgery contest — train a GAN from a 1-D toy demo in your browser up to a DCGAN that draws handwritten digits.