Newton's First Law of Motion
Last edited: August 8, 2025\begin{equation} y’’=0 \end{equation}
that is, if \(F=0\), then the solution will travel along a straight line.
Newton's Law of Cooling
Last edited: August 8, 2025Putting something with a different temperature in a space with a constant temperature. The assumption underlying here is that the overall room temperature stays constant (i.e. the thing that’s cooling is so small that it doesn’t hurt room temperature).
\begin{equation} y’(t) = -k(y-T_0) \end{equation}
where, \(T_0\) is the initial temperature.
The intuition of this modeling is that there is some \(T_0\), which as the temperature \(y\) of your object gets closer to t. The result we obtain
NL
Last edited: August 8, 2025\begin{equation} \text{NL} = \text{NSPACE} \qty( \log n) \end{equation}
See also Certificates-Based Intepretation of NL
problems in \(NL\)
We can see \(L \subseteq NL\), because a TM is a NTM.
STCONN is in NL
On input \(\qty(G, s,t)\), if \(s = t\), accept; otherwise,
- currNode = 5
- numSteps = 0
- while steps <= n
- non-deterministically choose a next node
- update currNode = w
- if w = t, accept
- set numSteps ++
- reject
so we just have to remember the current node. So this whole thing is \(O\qty(\log n)\).
NLP
Last edited: August 8, 2025Coherence
Generative REVOLUTION
Why probability maximization sucks
Its expensive!
Beam Search
- Take \(k\) candidates
- Expand \(k\) expansions for each of the \(k\) candidates
- Choose the highest probability \(k\) candidates
\(k\) should be small: trying to maximizing
Branch and Bound
See Branch and Bound
Challenges of Direct Sampling
Direct Sampling sucks. Its sucks. It sucks. Just sampling from the distribution sucks. This has to do with the fact that assigning slightly lower scores “being less confident” is exponentially worse.
NLP Index
Last edited: August 8, 2025Learning Goals
- Effective modern methods for deep NLP
- Word vectors, FFNN, recurrent networks, attention
- Transformers, encoder/decoder, pre-training, post-training (RLHF, SFT), adaptation, interoperability, agents
- Big picture in HUMAN LANGUAGES
- why are they hard
- why using computers to deal with them are doubly hard
- Making stuff (in PyTorch)
- word meaning
- dependency parsing
- machine translation
- QA
