> For the complete documentation index, see [llms.txt](https://www.mlcompendium.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.mlcompendium.com/deep-learning/intro.md). # Introduction A network learns features the earlier chapters had to specify by hand, and there is no linear-algebra page and no classical computer-vision page in this book. After this chapter the reader can follow a net from the gradient to the architecture and can place vision, audio, tabular, and sequence nets on that map. The chapter goes in that order: first how a net is trained, then the architectures built on that training, then the modalities those architectures are applied to. ## Training Training starts with the gradient, so [Calculus](/deep-learning/calculus.md) comes first, as the starting point for the matrix calculus used when differentiating through neural nets. [Game Theory](/deep-learning/game-theory.md) follows, for game theory as it shows up in computer science and AI. With those in hand, [Deep Neural Nets Basics](/deep-learning/deep-neural-nets.md) covers the building blocks of deep nets (perceptrons, multilayer networks, activations, and loss) and how training runs, from gradient descent, batch size, learning rate, and optimizers to batch normalization, dropout, and reading train/val accuracy. Once a net trains, [Deep Network Optimization](/deep-learning/deep-network-optimization.md) is about making it smaller or more teachable through pruning, knowledge distillation, and lottery tickets, and about debugging nets that fail to train. [Deep Neural Frameworks](/deep-learning/deep-neural-frameworks.md) closes the part with the libraries used in practice, PyTorch, fast.ai, and Keras, and the NVIDIA CUDA stack that runs them on a GPU. ## Architectures The same training loop drives very different shapes of network. [Autoencoders](/deep-learning/autoencoders.md) are the reconstruction setups used for dimensionality reduction, with variational autoencoders after the basics. [Convolutional Nets](/deep-learning/convolutional-nets.md) are the nets for vision-style feature learning, with capsule nets, transfer learning, and visualization of what they learn. [Recurrent Nets](/deep-learning/recurrent-nets.md) handle sequences and time series with back propagation, LSTM and GRU cells, and related variants. The [Attention](/deep-learning/attention.md) notes have moved on to the Transformers and pretrained language model pages, and [Transformers](/deep-learning/transformers.md) collects the illustrated guides and papers on the Transformer architecture and its family of variants. [Bayesian Neural Nets](/deep-learning/bayesian-neural-nets.md) add prediction uncertainty to a net. [Graph Neural Nets](/deep-learning/graph-neural-nets.md) cover graph convolutional networks and node-embedding methods such as DeepWalk and Node2vec. [Siamese Nets](/deep-learning/siamese-nets.md) learn a similarity between inputs for one-shot learning rather than a flat class label. [Other Architectures](/deep-learning/other-architectures.md) gathers the families beyond standard deep nets: self-organizing maps, neuro-evolution, RBFNs, and signal-processing networks. [Representations](/deep-learning/representations.md) is the embedding page, from entity embeddings and \*2vec techniques to vector similarity search. [Meta Learning (AutoML)](/deep-learning/meta-learning.md) ends the part by automating model choice, hyperparameters, and architecture search. ## Modalities The architectures then meet a kind of data. [Deep Neural Machine Vision](/deep-learning/deep-neural-machine-vision.md) covers detection, recognition, and segmentation in machine vision. [Deep Neural Audio](/deep-learning/deep-neural-audio.md) collects models for speech, sound classification, and related audio tasks. [Deep Neural Tabular](/deep-learning/deep-neural-tabular.md) points at TabNet and at surveys of deep learning on tabular data. [Deep Neural Time Series](/deep-learning/deep-neural-time-series.md) points at NeuralProphet for deep neural time-series forecasting. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.mlcompendium.com/deep-learning/intro.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.