
- Home
- Books
- Artificial Intelligence & Machine Learning
- Deep Learning & Neural Networks
- Fundamentals of Deep Learning, 2nd Edition
Fundamentals of Deep Learning by Nithin Buduma is a practical guide to the mathematical principles and neural network architectures powering modern AI. Deep neural networks require understanding both underlying mathematical mechanics and practical framework implementations. Buduma explains how gradient descent, loss landscapes, and layer configurations dictate model convergence across vision, sequence, and generative tasks.
What you will learn
- Derive backpropagation, gradient descent algorithms, and loss functions from mathematical first principles
- Design feedforward and multi-layer perceptron networks with appropriate activation functions and regularizers
- Construct convolutional neural networks for feature extraction, image classification, and object recognition
- Implement recurrent neural networks, gated recurrent units, and LSTMs for sequential and time-series data
- Apply self-attention mechanisms and Transformer layers to complex natural language problems
- Train generative adversarial networks and variational autoencoders to synthesize high-dimensional data
- Translate theoretical network architectures into working code using modern deep learning libraries
Who this is for
Software engineers, data analysts, and computer science students looking to bridge the gap between machine learning theory and deep neural network code. Basic Python proficiency and introductory calculus are assumed.


