These are basically MDP methods but tweaked. We make some changes:

1. for everywhere that we need a state, we use a belief
2. to sample the next state given an action (random next step), we call our generative model to get a new observation, and call update(b,a,o) with our filter to propegate our belief forward
3. if we need an action-value, we use the one-step lookahead in POMDP:

\begin{equation} Q(b,a) = R(b,a)+\gamma \qty(\sum_{o}^{}P(o|b,a) U^{\Gamma}(update(b,a,o))) \end{equation}

where,

\begin{equation} R(b,a) = \sum_{s}^{} R(s,a)b(s) \end{equation}

The Open Voice Brain Model is a audio processing architecture proposed by Laguarta 2021 for audio/biomarker correlation work.

Here’s a fairly self-explanatory figure:

The model outputs an AD diagnoses as well as a longitudinal correlation with Memory, Mood, and Respiratory biomarkers.

This is then the embedding that they are proposing for use by other tasks.

OpenSMILE is a proprietary audio feature exaction tool.

Site.

cs111.stanford.edu

Topics

CS111 leverages CS107 experience to show operating systems and how they function.

What is an operating system

• operating system sits between hardware and user programs
• most importantly: manages shared resources to allow the program to run
  • CPU: gets which program to do work and for how long
  • RAM: how much memory to give to a program
  • Hard Drive

Main Events

• concurrency: switch between processes so quickly to only use on core while concurrent access
• memory: memory addresses are mostly scattered everywhere — everything include the lowest level including CPU uses only virtual memory, translated by the OS
• file management
• i/o devices
• networking: CS144
• security: interactions between users in a system

Main Components of the Course

• File Systems
• Process and Multiprocess
• Threads
• Virtual Memory + Paging + limits
• Modern Technologies/Niceties

What’s Next

SU-CS111 Outline

• adding
• multiplying

This is object dependent.