CMU 10-414/714: Deep Learning Systems

Author

Chao Ma

Published

June 12, 2026

Notes from CMU 10-414/714 Deep Learning Systems, focused on the systems and mathematical foundations needed to build deep learning workloads.

Lecture 3 Part II: Manual Neural Networks Manual backpropagation for two-layer networks, matrix gradients, upstream error signals, vector-Jacobian products, and forward/backward passes.

Lecture 3: Manual Neural Networks Linear hypothesis limitations, feature maps, nonlinear activations, two-layer networks, ReLU, fully connected networks, and why depth helps in practice.

Lecture 2: ML Refresher / Softmax Regression Hypothesis classes, loss functions, optimization, softmax regression, cross-entropy, gradient descent, SGD, and the softmax gradient.

---
title: "CMU 10-414/714: Deep Learning Systems"
author: "Chao Ma"
date: "2026-06-12"
---

Notes from CMU 10-414/714 Deep Learning Systems, focused on the systems and mathematical foundations needed to build deep learning workloads.

---

::: {.content-grid}

::: {.content-card}
**[Lecture 3 Part II: Manual Neural Networks](cmu-dlsys-lecture-3-part-2-manual-neural-networks.qmd)**
Manual backpropagation for two-layer networks, matrix gradients, upstream error signals, vector-Jacobian products, and forward/backward passes.
:::

::: {.content-card}
**[Lecture 3: Manual Neural Networks](cmu-dlsys-lecture-3-manual-neural-networks.qmd)**
Linear hypothesis limitations, feature maps, nonlinear activations, two-layer networks, ReLU, fully connected networks, and why depth helps in practice.
:::

::: {.content-card}
**[Lecture 2: ML Refresher / Softmax Regression](cmu-dlsys-lecture-2-ml-refresher-softmax-regression.qmd)**
Hypothesis classes, loss functions, optimization, softmax regression, cross-entropy, gradient descent, SGD, and the softmax gradient.
:::

:::