--- title: Deep Learning description: This subset of machine learning utilizes multi-layered artificial neural networks to model complex patterns in data. Learners will understand how to design, train, and evaluate deep neural architectures for tasks like image recognition and natural language processing. category: programming-tech subcategory: artificial-intelligence difficulty: beginner, intermediate, advanced url: /subject/deep-learning --- # Deep Learning This subset of machine learning utilizes multi-layered artificial neural networks to model complex patterns in data. Learners will understand how to design, train, and evaluate deep neural architectures for tasks like image recognition and natural language processing. ## Available Resources 2 Videos • 5 Books • 7 Courses • 6 Websites • 2 Papers ## Websites ### 1. Deep (Learning) Focus **Author:** Cameron R. Wolfe Cameron R. Wolfe's newsletter, which takes one deep learning research topic at a time and walks through several papers on it in sequence, supplying the background needed to read the primary literature yourself. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://cameronrwolfe.substack.com/ **Tags:** deep-learning, llm, research-summaries, transformers, language-models ### 2. Deep Learning Book The full text of the MIT Press textbook by Goodfellow, Bengio, and Courville, free to read online. Covers the linear algebra and probability groundwork, feedforward networks, regularization, optimization, CNNs, RNNs, and research topics such as generative models. **Difficulty:** Beginner | **Price:** Free **Link:** https://www.deeplearningbook.org/ **Tags:** deep-learning, neural-networks, machine-learning, optimization, textbook ### 3. Dive into Deep Learning An open-source textbook where every model is presented with runnable code in PyTorch, TensorFlow, and JAX alongside the math. Working through it, you implement linear regression, CNNs, RNNs, attention, and transformers yourself in Jupyter notebooks. **Difficulty:** Beginner | **Price:** Free **Link:** https://d2l.ai/ **Tags:** deep-learning, pytorch, neural-networks, jupyter, textbook ### 4. Distill.pub Peer-reviewed web journal of machine learning explanations, publishing interactive articles on topics like feature visualisation, attention and neural network interpretability. Archive remains readable, though the journal went on indefinite hiatus in 2021 and no longer publishes. **Difficulty:** Intermediate | **Price:** Free **Link:** https://distill.pub/ **Tags:** deep-learning, neural-networks, interpretability, interactive-visualization, machine-learning ### 5. deeplearning.ai deeplearning.ai is an education platform focused on making AI and deep learning accessible through practical online courses and programs, including the Deep Learning Specialization and AI for Everyone. It offers structured curricula with video lessons, labs, assignments, and certificates covering neural networks, deep learning, TensorFlow, NLP, and broader AI topics. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://deeplearning.ai **Tags:** websites, technology-computer-science, ai-ml ### 6. cs231n.stanford.edu Stanford's CS231n course site for Convolutional Neural Networks for Visual Recognition, offering lecture notes, slide decks, assignments, and project materials that teach deep learning techniques for computer vision. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://cs231n.stanford.edu **Tags:** websites, technology-computer-science, ai-ml ## Books ### 1. Build a Large Language Model (From Scratch) **Author:** Sebastian Raschka Sebastian Raschka's Manning book walks through coding a GPT-style model in PyTorch step by step: tokenization, attention, the transformer block, pretraining on unlabeled text, then fine-tuning for classification and instruction following. **Difficulty:** Intermediate | **Language:** English | **Price:** Paid **Link:** https://www.amazon.com/dp/1633437167?tag=edmonddante07-20 **Tags:** llm, transformers, pytorch, fine-tuning, from-scratch ### 2. Understanding Deep Learning **Author:** Simon J.D. Prince Simon Prince's MIT Press textbook, free to read online, works through neural network fundamentals, backpropagation, convolutional and transformer architectures, generative models, and reinforcement learning, with exercises and notebooks that build the mathematics behind each method. **Difficulty:** Intermediate | **Language:** English | **Price:** Paid **Link:** https://www.amazon.com/dp/0262048647?tag=edmonddante07-20 **Tags:** deep-learning, neural-networks, transformers, machine-learning-theory ### 3. Deep Learning with PyTorch, Second Edition **Author:** Luca Antiga, Eli Stevens, Howard Huang, Thomas Viehmann A 2026 rewrite co-authored by PyTorch core developers, covering tensors, autograd, and the training loop before moving to transformers, diffusion models, and deployment. Ends with a full medical imaging project, so readers finish having shipped a non-toy model. **Difficulty:** Intermediate | **Language:** English | **Price:** Paid **Link:** https://www.amazon.com/dp/1633438856?tag=edmonddante07-20 **Tags:** pytorch, deep-learning, autograd, neural-networks, transformers ### 4. Neural Networks and Deep Learning **Author:** Michael Nielsen A foundational and widely acclaimed online book that explains neural networks and deep learning concepts from scratch, with clear explanations and interactive examples. It's an excellent resource for building a strong theoretical understanding. **Difficulty:** Beginner | **Language:** English | **Price:** Free **Link:** https://neuralnetworksanddeeplearning.com/ **Tags:** neural-networks, backpropagation, gradient-descent, deep-learning, free-textbook ### 5. Deep Learning with Python **Author:** François Chollet Chollet, the creator of Keras, teaches neural networks through worked Keras examples in computer vision, text, and time series, with chapters on the intuition behind representation learning. Assumes Python fluency but no prior machine learning. **Difficulty:** Intermediate | **Language:** English | **Price:** Paid **Link:** https://www.amazon.com/dp/1617294438?tag=edmonddante07-20 **Tags:** books, technology-computer-science, ai-ml ## Courses ### 1. Neural Networks: Zero to Hero Learn deep learning from scratch with Andrej Karpathy's "Neural Networks: Zero to Hero" course! Build your AI expertise today. **Difficulty:** Beginner | **Price:** Free **Link:** https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ **Tags:** neural-networks, backpropagation, pytorch, transformers, language-models ### 2. Neural Networks: Zero to Hero **Author:** Andrej Karpathy Free video lecture series building neural networks from scratch in Python: the micrograd autograd engine, character-level language models, MLPs, activations and batch normalization, manual backpropagation, WaveNet, and a GPT with its tokenizer. Requires solid Python and introductory calculus; learners can implement and train transformers themselves. **Difficulty:** Intermediate | **Price:** Free **Link:** https://karpathy.ai/zero-to-hero.html **Tags:** neural-networks, backpropagation, language-models, transformers, pytorch ### 3. Practical Deep Learning for Coders fast.ai's free course teaching deep learning top-down: you train working image, text, and tabular models in the first lessons, then work back to the underlying mechanics. Assumes about a year of coding experience, uses PyTorch and the fastai library. **Difficulty:** Beginner | **Price:** Free **Link:** https://course.fast.ai/ **Tags:** deep-learning, pytorch, fastai, computer-vision, top-down-teaching ### 4. Introduction to Deep Learning (MIT 6.S191) **Author:** Alexander Amini, Ava Amini Annual one-week bootcamp on deep learning: neural network foundations, sequence models and transformers, convolutional networks for vision, generative models, and reinforcement learning. Recorded lectures, slides and software labs in TensorFlow and PyTorch let learners build and train working models. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://introtodeeplearning.com/ **Tags:** deep-learning, neural-networks, transformers, convolutional-neural-networks, generative-models ### 5. Andrew Ng's Deep Learning Specialization This specialization is one of the most popular and comprehensive introductions to deep learning. It covers foundational concepts of neural networks, including how to build and train them, and delves into convolutional networks, recurrent networks, and more. While the certificate requires payment, auditing the courses (watching lectures, accessing many materials) is typically free. **Difficulty:** Beginner | **Language:** English | **Price:** Free **Link:** https://www.coursera.org/specializations/deep-learning **Tags:** deep-learning, neural-networks, convolutional-neural-networks, recurrent-neural-networks, hyperparameter-tuning ### 6. Deep Learning RWTH Aachen University course on neural networks and their training, covering multi-layer perceptrons, training techniques, convolutional and recurrent networks, and transformers, with an outlook on efficient fine-tuning of large multimodal models. Learners can explain and train the main deep architectures. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://www.edx.org/learn/computer-science/rwth-aachen-university-deep-learning-4 **Tags:** neural-networks, convolutional-neural-networks, recurrent-neural-networks, transformers, model-training ### 7. Machine Learning: Deep & Reinforcement Learning An IBM course on edX covering neural network fundamentals, backpropagation and optimizers, convolutional and recurrent networks, autoencoders and generative models, with a closing introduction to reinforcement learning. Learners can build and train deep learning models in Python with Keras. **Difficulty:** Intermediate | **Language:** English | **Price:** Free **Link:** https://www.edx.org/learn/computer-science/ibm-deep-learning-and-reinforcement-learning **Tags:** deep-learning, neural-networks, convolutional-neural-networks, recurrent-neural-networks, reinforcement-learning ## Podcasts ### 1. The TWIML AI Podcast **Author:** Sam Charrington Long-running interview podcast hosted by Sam Charrington in which ML and AI researchers and practitioners discuss their work on deep learning, natural language processing, neural networks and data science, helping listeners follow current research and how it is applied in industry. **Difficulty:** Intermediate | **Language:** en | **Price:** Free **Link:** https://twimlai.com **Tags:** machine-learning, artificial-intelligence, deep-learning, ai-research ## Papers ### 1. ImageNet Classification with Deep Convolutional Neural Networks **Author:** Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton This paper introduced AlexNet, a groundbreaking convolutional neural network that significantly outperformed previous methods in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012. It marked a turning point for deep learning's resurgence and practical application. **Difficulty:** Advanced | **Language:** English | **Price:** Free **Link:** https://proceedings.neurips.cc/paper/2012/file/c399862d3b4b6b014381395edb6697af-Paper.pdf **Tags:** convolutional-neural-networks, imagenet, computer-vision, deep-learning, alexnet ### 2. Deep Learning **Author:** Yann LeCun, Yoshua Bengio, Geoffrey Hinton A seminal review paper by three pioneers of deep learning, providing an overview of the field, its history, key concepts, and future directions. It's an excellent read for understanding the landscape of deep learning. **Difficulty:** Advanced | **Language:** English | **Price:** Free **Link:** https://www.nature.com/articles/nature14539 **Tags:** deep-learning, neural-networks, representation-learning, backpropagation, review-paper ## Videos ### 1. StatQuest with Josh Starmer - Neural Networks videos Josh Starmer's StatQuest provides clear, concise, and often humorous explanations of statistical and machine learning concepts. His videos on neural networks break down complex ideas into easily digestible 'quests.' **Difficulty:** Beginner | **Language:** English | **Price:** Free **Link:** https://www.youtube.com/playlist?list=PLXe8IwAUB2B-Ews9ADFJBHE7nVAZAfV05 **Tags:** neural-networks, backpropagation, machine-learning, statistics, video-series ### 2. 3Blue1Brown - Neural Networks series Grant Sanderson's 3Blue1Brown channel offers visually intuitive and mathematically rigorous explanations of complex topics. His series on neural networks is particularly praised for making the core concepts, like backpropagation, understandable through animated visuals. **Difficulty:** Beginner | **Language:** English | **Price:** Free **Link:** https://www.youtube.com/playlist?list=PLW_xnxm7jEso **Tags:** neural-networks, backpropagation, gradient-descent, deep-learning, visual-explanation --- *This content is part of Dantes.io - Your Treasure Map to Knowledge* *Curated by humans at Dantes.io. Personal study use welcome; republishing this curation requires permission (team@dantes.io).* View this page online: https://dantes.io/subject/deep-learning