Monthly Archives: March 2025

Exam 02 Logistics: Practicum

This post outlines the Practicum 2 part of Exam 2. See the in-person Exam 2 or Practicum 2 Update posts for details on the other parts. Study exams are in the Box folder.

  • Modules: 06 – 08
  • When: Friday 4/4 12:01am to Saturday 4/5 11:59pm
    • There is no class on Friday.
    • It should take you (and your partner) around 3-6 hours to complete, but you can take as long as you want. It must be submitted before the end of the Saturday.
    • NOTE: The expected hours to complete is longer than Practicum 1’s estimate.
  • All other details are the same as Practicum 1’s logistics.

Exam 02 Logistics: In-Person Exam

This post outlines the in-person part of Exam 2. See the Practicum 2 or Practicum 2 Update posts for details on the other parts.

  • Modules covered: 06 – 08
  • When: Wednesday 4/2, during regular class time
  • A calculator is strongly recommended. But if you forget, you will be okay because no exact calculations are required.
  • The formulas you will need are printed on the exam’s front page. See an example on the study exam.
  • Code on the exam
    • The data set used for this exam is Seaborn’s diamonds data set. We recommend familiarizing yourself with the columns’ meanings.
    • It will have code reading (so know what these functions do), in particular:
      • The results of calling the describe function on a data set.
      • The results of a seaborn function call: groupby and pivot_table
  • All other details are the same as In-person Exam 1’s logistics, including:
    • You will not write code.
    • We will release a study exam and Canvas study quiz.
    • You may bring one piece of paper as a helper sheet and can put things on the front and back.

Grading Scale and Points Allocation

This is the same as Exam 1’s logistics in that problems are graded on an ESNU scale. How many points each rubric level is worth depends on the question. A question’s worth depends on how many questions in the exam are testing the same concept (more questions for that concept means fewer points for each question). The goal is that an exam with only S’s on every question results in a 90% because it indicates a Satisfactory level of understanding of all the concepts the exam is testing, rather than Exemplary.

Exam 02 Logistics: Practicum Update

This post outlines the Practicum 2 Update part of Exam 2. See the in-person Exam 2 or Practicum 2 posts for details on the other parts. Study exams are in the Box folder.

  • When: Thursday 4/10 – Saturday 4/12
    • Wednesday 4/9’s class will cover general feedback on Practicum 2.
    • Friday 4/11’s class is optional and will be for Project consulting or questions on Practicum 2. Prof. Stephens-Martinez will run it over Zoom and will be in her office if you want to ask her in person.
  • All other details are the same as Practicum 1 Update’s logistics.

Module 10: Deep Learning

  1. Prepare (due Monday 4/14)
    1. Content below
    2. Canvas quizzes
  2. Class engagement – See on the class forum
  3. Homework (due Sun 4/20, late due 4/23) [Link]
  4. There are no worked examples

Content

10 Deep Learning

  1. Neural Networks and Applications (16 min.)
  2. Forward Propagation (10 min.)
  3. Gradient Descent (14 min.)
  4. Back Propagation (11 min.)
  5. Convolutional Neural Network (15 min.)
  6. Introducing Pytorch (23 min.)

Optional Supplements

Pytorch

Unlike most other libraries for this course, Pytorch is not included in the basic Anaconda installation. To use Pytorch, we suggest you choose one of two options.

  • Install Pytorch locally (for free). You can see the directions on the website: Select the stable build, your operating system, Conda (for Anaconda), Python, and CPU to see install directions for your particular setup. (CUDA is used to support hardware acceleration with NVIDIA graphics cards and is not necessary for this course).
  • Use Pytorch in a Jupyter notebook in the cloud (also for free). The easiest way to do this if you have a Google account is with a Google colab notebook; Pytorch will already be available to you in this cloud environment.

You can find the official Pytorch documentation here. Of particular note are the Pytorch tutorials, including Pytorch recipes which serve as small examples of common tasks.

Book

The deep learning book is available free online and is authored by some of the leading experts in machine learning with deep artificial neural networks. It is very detailed and in-depth and is purely for those who are interested in learning more about deep learning theory now or in the future; you do not need to read the book for this course.