> ## Documentation Index
> Fetch the complete documentation index at: https://aegean.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Computer Vision Weekly Study Guide

> Week-by-week study guide for the Deep Learning for Computer Vision course.

See the [Spring 2026 Academic Calendar](/courses/calendar) for semester dates. Each week below lists the readings, lecture topics, and deliverables you should complete.

<AccordionGroup>
  <Accordion title="Week 1, Introduction">
    <Steps>
      <Step title="Read TIF Chapter 1">
        The challenge of vision from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Review prerequisites">
        Python, linear algebra, probability theory, and camera fundamentals. See [Prerequisites](/book/prerequisites/index).
      </Step>

      <Step title="Review lecture: Introduction">
        Computer vision for agents with egomotion. Course roadmap and overview.
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> [How We Understand Scenes](https://www.youtube.com/watch?v=9CGGh6ivg68), Human Perception and Imaging.

        <Icon icon="video" /> [Mathematical Prerequisites](https://www.youtube.com/watch?v=jkNugBJG2yk), Review the math foundations needed for the course.
      </Step>

      <Step title="Set up your development environment">
        Follow the [Dev Environment](/aiml-common/resources/environment/index) guide to install Docker and configure your container.
      </Step>

      <Step title="Import the course repository">
        [Import](https://docs.github.com/en/migrations/importing-source-code/using-github-importer/importing-a-repository-with-github-importer) [eng-ai-agents](https://github.com/pantelis/eng-ai-agents) to your GitHub account and clone it locally.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 2, Statistical Learning Theory">
    <Steps>
      <Step title="Read TIF Chapters 9 & 10">
        Introduction to learning and gradient-based learning algorithms from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Read BISHOP Chapters 4 & 5">
        Single-variable and multivariate models, regularization, Bayesian linear regression, and single-layer networks from [Deep Learning: Foundations and Concepts](https://www.bishopbook.com/).
      </Step>

      <Step title="Review lecture: Supervised Learning">
        Perception subsystem, reflexive agents, the learning problem. See [The Learning Problem](/aiml-common/lectures/learning-problem/index).
      </Step>

      <Step title="Review lecture: Linear Regression">
        Regression fundamentals and empirical risk minimization. See [Linear Regression](/aiml-common/lectures/regression/linear-regression/index).
      </Step>

      <Step title="Review lecture: SGD Optimization">
        Stochastic gradient descent for minimizing the empirical risk. See [SGD](/aiml-common/lectures/optimization/sgd/index).
      </Step>

      <Step title="Read GERON Chapter 4, SGD sections">
        Read the Gradient Descent, Batch Gradient Descent, Stochastic Gradient Descent, and Mini-Batch Gradient Descent sections from [Chapter 4: Training Linear Models](https://learning.oreilly.com/library/view/hands-on-machine-learning/9798341607972/ch04.html).
      </Step>

      <Step title="Run the GERON Chapter 4 notebook">
        Work through the [Training Linear Models](https://github.com/ageron/handson-mlp/blob/main/04_training_linear_models.ipynb) notebook.
      </Step>

      <Step title="Run the SGD notebook">
        Execute the [SGD Sinusoidal Dataset](/aiml-common/lectures/regression/linear-regression/sgd_sinusoidal_dataset) notebook in your container.
      </Step>

      <Step title="Review lecture: Entropy">
        Information theory principles and cross-entropy. See [Entropy](/aiml-common/lectures/entropy/index).
      </Step>

      <Step title="Review lecture: Marginal Maximum Likelihood">
        Marginal likelihood and parameter estimation. See [Marginal Maximum Likelihood](/aiml-common/lectures/optimization/maximum-likelihood/marginal_maximum_likelihood).
      </Step>

      <Step title="Review lecture: Conditional Maximum Likelihood">
        Conditional likelihood for supervised learning. See [Conditional Maximum Likelihood](/aiml-common/lectures/optimization/maximum-likelihood/conditional_maximum_likelihood).
      </Step>

      <Step title="Review lecture: Classification Introduction">
        Classification fundamentals and decision boundaries. See [Classification Introduction](/aiml-common/lectures/classification/classification-intro/index).
      </Step>

      <Step title="Review lecture: Logistic Regression">
        Binary classification with logistic regression. See [Logistic Regression](/aiml-common/lectures/classification/logistic-regression/index).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Statistical learning theory video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 3, Dense Neural Networks">
    <Steps>
      <Step title="Read TIF Chapters 12 & 13">
        Neural networks and neural networks as distribution transformers from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Read BISHOP Chapter 6">
        Cross entropy loss, training and regularization of dense layers from [Deep Learning: Foundations and Concepts](https://www.bishopbook.com/).
      </Step>

      <Step title="Review lecture: DNN Introduction">
        Forward pass and neural network architectures. See [DNN Introduction](/aiml-common/lectures/dnn/dnn-intro/index).
      </Step>

      <Step title="Run the Fashion MNIST notebook">
        Execute the [Fashion MNIST Case Study](/aiml-common/lectures/dnn/fashion-mnist-case-study) notebook in your container.
      </Step>

      <Step title="Run the GERON Chapter 9 notebook">
        Work through the [Artificial Neural Networks](https://github.com/ageron/handson-mlp/blob/main/09_artificial_neural_networks.ipynb) notebook.
      </Step>

      <Step title="Submit Assignment 1">
        Complete and submit [Assignment 1](/aiml-common/assignments/main/cv-spring-2026/assignment-1).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Dense neural networks video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 4, CNNs">
    <Steps>
      <Step title="Read TIF Chapter 24, BISHOP Chapter 10">
        Convolutional Neural Network architecture and applications from [Foundations of Computer Vision](https://visionbook.mit.edu/) and [Deep Learning: Foundations and Concepts](https://www.bishopbook.com/).
      </Step>

      <Step title="Review lecture: CNN Introduction">
        Convolution operations, pooling, and spatial feature hierarchies. See [CNN Introduction](/aiml-common/lectures/cnn/cnn-intro/index).
      </Step>

      <Step title="Review lecture: CNN Layers, Architectures and ResNets">
        Layer types, architectural patterns, ResNet, and VGG. See [CNN Layers](/aiml-common/lectures/cnn/cnn-layers/index), [CNN Example Architectures](/aiml-common/lectures/cnn/cnn-example-architectures/index), and [Feature Extraction with ResNet](/aiml-common/lectures/scene-understanding/feature-extraction-resnet/index).
      </Step>

      <Step title="Read GERON Chapter 12, CNN sections">
        Read the Convolutional Layers, Pooling Layers, and CNN Architectures sections from [Chapter 12: Deep Computer Vision with CNNs](https://learning.oreilly.com/library/view/hands-on-machine-learning/9798341607972/ch12.html).
      </Step>

      <Step title="Run the GERON Chapter 12 notebook">
        Work through the [Deep Computer Vision with CNNs](https://github.com/ageron/handson-mlp/blob/main/12_deep_computer_vision_with_cnns.ipynb) notebook.
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> [Convolution and Correlation](https://www.youtube.com/watch?v=WXoOohWU28Y), A linear operation for extracting spatial features.

        <Icon icon="video" /> [CNN Architectures](https://www.youtube.com/watch?v=TV-DjM8242s), Looking inside a CNN layer and understanding architectural patterns.

        <Icon icon="video" /> [Image Classification](https://www.youtube.com/watch?v=rCVlIVKqqGE), Image classification with data augmentation.

        <Icon icon="video" /> [What CNNs Learn](https://www.youtube.com/watch?v=lb_5AdUpfuA), Visualizing the features learned by CNNs.

        <Icon icon="video" /> [ResNets](https://www.youtube.com/watch?v=FCQ-rih6cHY), Residual Networks and skip connections.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 5, Object Detection">
    <Steps>
      <Step title="Read TIF Chapter 50">
        Object recognition from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Review lecture: Detection Metrics">
        Evaluation metrics for object detection. See [Detection Metrics](/aiml-common/lectures/scene-understanding/object-detection/detection-metrics/index).
      </Step>

      <Step title="Review lecture: Object Detection">
        Detection pipelines and architectures. See [Object Detection Introduction](/aiml-common/lectures/scene-understanding/object-detection/object-detection-intro/index).
      </Step>

      <Step title="Review lecture: R-CNN">
        Region-based convolutional neural networks. See [R-CNN](/aiml-common/lectures/scene-understanding/object-detection/rcnn/index).
      </Step>

      <Step title="Review lecture: Fast R-CNN">
        Efficient region-based detection. See [Fast R-CNN](/aiml-common/lectures/scene-understanding/object-detection/fast-rcnn/index).
      </Step>

      <Step title="Review lecture: Faster R-CNN">
        Region proposal networks and two-stage detection. See [Faster R-CNN](/aiml-common/lectures/scene-understanding/object-detection/faster-rcnn/index).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> [Introduction to Object Detection](https://www.youtube.com/watch?v=ojb-E4tDTxs), Object detection in a physical security application.

        <Icon icon="video" /> [Computer Vision Datasets](https://www.youtube.com/watch?v=YNBPJx0EUcc), What types of annotations are used in computer vision?

        <Icon icon="video" /> [Region-based Object Detectors](https://www.youtube.com/watch?v=4WHFcqq1ErA), R-CNN, Fast R-CNN, Faster R-CNN.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 6, Object Tracking">
    <Steps>
      <Step title="Read TIF Chapter 5">
        Imaging fundamentals from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Read: State Estimation">
        HMMs, Bayes Filter, Kalman Filter, and Particle Filters. See [State Estimation](/book/state-estimation/index).
      </Step>

      <Step title="Review lecture: Recursive State Estimation">
        Probabilistic reasoning over time for object tracking. See [Recursive State Estimation](/aiml-common/lectures/rse/recursive-state-estimation/index).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Object tracking video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 7, Midterm Exam">
    <Steps>
      <Step title="Midterm exam">
        The midterm covers weeks 1-6: statistical learning theory, dense neural networks, CNNs, object detection, and object tracking. See the [Faster R-CNN HPO exam notebook](/aiml-common/assignments/topics/hpo/torchvision-frcnn/torchvision-frcnn-hpo).
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 8, Vision Transformers">
    <Steps>
      <Step title="Read BISHOP Chapter 12, TIF Chapter 26">
        Self-attention for global image dependencies, ViT vs CNN trade-offs.
      </Step>

      <Step title="Review lecture: Transformers">
        Self-attention and multi-head attention. See [Transformers Introduction](/aiml-common/lectures/nlp/transformers/transformers-intro).
      </Step>

      <Step title="Review lecture: Transfer Learning">
        Pretrained models and fine-tuning. See [Transfer Learning](/aiml-common/lectures/transfer-learning/transfer-learning-introduction).
      </Step>

      <Step title="Run the GERON Chapter 16 notebook">
        Work through the [Vision and Multimodal Transformers](https://github.com/ageron/handson-mlp/blob/main/16_vision_and_multimodal_transformers.ipynb) notebook.
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> [Introduction to Transformers](https://www.youtube.com/watch?v=2pIIPXPopzc), The transformer architecture and the simple attention mechanism.

        <Icon icon="video" /> [The Learnable Attention Mechanism](https://www.youtube.com/watch?v=JdoXFcSiDrA), Implementing the scaled dot-product self attention mechanism.

        <Icon icon="video" /> [Multi-Head Self Attention](https://www.youtube.com/watch?v=hKCO8PO3yvw), Using multiple attention heads to capture different aspects of input sequences.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 9, Contrastive Learning">
    <Steps>
      <Step title="Read TIF Chapter 30">
        Representation learning from [Foundations of Computer Vision](https://visionbook.mit.edu/representation_learning.html).
      </Step>

      <Step title="Review lecture: CLIP">
        Contrastive learning and zero-shot classification. See [CLIP](/aiml-common/lectures/VLM/clip/index).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> [Contrastive Learning and CLIP](https://njit-edu.zoom.us/rec/share/iSTiylp128sFJcVbki1VqTbcL__LCf7bhnzrODSGoaHPL9ZwbUSBGwb8F1UEShpY.v_ypBfBux9pam7bv), Vision-language pretraining and zero-shot classification.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 10, Finetuning Vision Language Models">
    <Steps>
      <Step title="Review lecture: LLaVA">
        Visual instruction tuning for multimodal understanding. See [LLaVA](/aiml-common/lectures/VLM/llava/index).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Vision-language models video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 11, Prompted Vision Models">
    <Steps>
      <Step title="Review lecture: SAM">
        Meta's Segment Anything Model as a worker receiving multimodal prompts from VLM planners.
      </Step>

      <Step title="Explore SAM demos">
        Experiment with SAM for interactive segmentation tasks using different prompt types (points, boxes, text).
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Prompted vision models video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 12, Neural Radiance Fields">
    <Steps>
      <Step title="Read TIF Chapter 45">
        Radiance fields from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Review lecture: NeRF">
        Creating 3D scenes from 2D images, volume rendering concepts.
      </Step>

      <Step title="Explore NeRF resources">
        Review NeRF implementations and understand the novel view synthesis pipeline.
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Neural radiance fields video lectures are in development.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Week 13, Diffusion Models and Review">
    <Steps>
      <Step title="Read TIF Chapters 32 & 34">
        Generative models and conditional generative models from [Foundations of Computer Vision](https://visionbook.mit.edu/).
      </Step>

      <Step title="Review lecture: Diffusion Models">
        Physics-inspired learning, conditional image generation, DALL-E and Stable Diffusion.
      </Step>

      <Step title="Run the GERON Chapter 18 notebook">
        Work through the [Autoencoders, GANs, and Diffusion Models](https://github.com/ageron/handson-mlp/blob/main/18_autoencoders_gans_and_diffusion_models.ipynb) notebook.
      </Step>

      <Step title="Complete any outstanding assignments">
        Ensure all assignments are submitted via GitHub and Canvas/Brightspace.
      </Step>

      <Step title="Final exam preparation">
        Review cross-cutting themes: how detection, segmentation, VLMs, and generative models form a complete vision pipeline.
      </Step>

      <Step title="Watch videos">
        <Icon icon="video" /> Coming soon, Diffusion models video lectures are in development.
      </Step>
    </Steps>
  </Accordion>
</AccordionGroup>

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/aegean-ai/eaia/edit/main/src/courses/cv/study-guides/weekly-guide.mdx) or [file an issue](https://github.com/aegean-ai/eaia/issues/new/choose).
</Callout>