
Hidden Markov model
31
MENTIONS
11
EPISODES
5
PODCASTS
Search complete. 31 mentions across 11 episodes found for "Hidden Markov model".
Nov 21, 2026
Content-Based Image and Video Retrieval
S
35:34Sanjeev KhudanpurGUEST
And third, Let's just allow captions which are actually seen.
S
35:39Sanjeev KhudanpurGUEST
In other words, if I've never seen a car, road, and building together, it's not allowed as a possible path through my HMMs.
S
35:45Sanjeev KhudanpurGUEST
Only paths which I've actually seen in training are allowed.
S
35:48Sanjeev KhudanpurGUEST
This doesn't mean that my captions coming out will only be captions in the training.
7 MINS LATER
S
42:24Sanjeev KhudanpurGUEST
So we have 13 individual video sources in our entire collection.
S
42:28Sanjeev KhudanpurGUEST
And so we went ahead and did this HMM training.
S
42:30Sanjeev KhudanpurGUEST
So what we did is we built up the HMMs first for everything, like all the images of all the sources for all the concepts.
S
42:38Sanjeev KhudanpurGUEST
And then we chopped up the data into the 13 individual subsets, one from each source, and re-estimated the HMM parameters on each subset.
Learning to Analyze Sequences
F
28:24Fernando PereiraGUEST
many of you will notice immediately, that's not tractable in general, because there are exponentially many y's.
F
28:32Fernando PereiraGUEST
So what we're going to do is that we're going to do exactly the same thing that people do for HMMs and probabilistic contextual grammars, which is to impose some kind of a Markov assumption into this inference problem.
F
28:48Fernando PereiraGUEST
So what we're going to do is think about this feature function as a sum of feature functions that look basically at all, can look at all of the input x, but only a little piece of y.
F
29:04Fernando PereiraGUEST
So a bounded piece of the output structure Y.
Incremental Bayesian Networks for Natural Language Parsing
M
25:26Mark JohnsonGUEST
I'll talk about that at the end.
M
25:31Mark JohnsonGUEST
So here's another example that might look a bit more familiar to people familiar with HMMs.
M
25:37Mark JohnsonGUEST
It's dependency parsing where we're just trying to recover these, these head dependent relationships.
M
25:43Mark JohnsonGUEST
We don't have internal structure.
Lawrence Reiter - research models for neurogenetic disorders
G
5:31Grant BelgardHOST
You decide what counts as a seizure phenotype in a fly, and how do you measure it?
L
5:38Lawrence ReiterGUEST
So you would understand this concept, right? We don't decide, right? We use hidden Markov modeling and we let the video just tell us, right? What's immobilization? What's walking? What's uncoordinated movement? And then we compare to the control group and look at statistically at effect sizes for drug treatment, right? So in most cases, good science, you don't decide, right? You just, you let the statistics and the animal decide for you.
G
6:07Grant BelgardHOST
How would you
L
6:08Lawrence ReiterGUEST
work out
P
Unknown podcast
Practical Probabilistic Programming
Nov 15 · 1 Mention
S
14:29speaker_2HOST
But the present moment rarely gives you the full picture, right? Especially in security, where adversaries actively hide their footprints.
S
14:36speaker_1HOST
That is exactly where hidden Markov models, or HMMs, come in.
S
14:40speaker_1HOST
In an HMM, the system models underlying states that you cannot observe directly, the hidden states.
S
14:47speaker_1HOST
What you can measure are the observable emissions generated by those states.
Bayesian Networks 9 - EM Algorithm | Stanford CS221: AI (Autumn 2021)
P
7:30Percy LiangHOST
So in case H is small, we can just do it kind of brute force.
P
7:35Percy LiangHOST
If H is HMM, we can use, if the Bayesian network is HMM, we can use forward-backward.
P
7:41Percy LiangHOST
In general, we can skip sampling, et cetera.
P
7:45Percy LiangHOST
So now what do we have? We have these weights for every H.
12 MINS LATER
P
20:18Percy LiangHOST
So now you hide the substitution table, and then you hand someone the ciphertext, or you put it in a book and bury it for someone to discover later.
P
20:30Percy LiangHOST
So now the question is when someone receives a ciphertext, is given the ciphertext, can they recover the plaintext? Importantly, the plaintext is obviously unknown, but also the substitution table is also unknown.
P
20:47Percy LiangHOST
So this is a very challenging problem, but let's see how we can use Bayesian networks, in particular HMM, to try to address this.
P
20:57Percy LiangHOST
So remember the process of using an HMM, you have to think about what is the generative story of how this data arose.
Bayesian Networks 3 - Probabilistic Programming | Stanford CS221: AI (Autumn 2021)
P
5:15Percy LiangHOST
then the trajectories are OK.
P
5:20Percy LiangHOST
So this program specifies what is called a Markov model, which is a special case of a Bayesian network where we have a chain.
P
5:30Percy LiangHOST
Each variable is only dependent on the previous
P
5:32Percy LiangHOST
variable.
P
5:37Percy LiangHOST
With this
P
5:38Percy LiangHOST
Markov model, we can ask particular questions.
P
5:40Percy LiangHOST
For example, what are the possible trajectories given the evidence X10 equals A2? So here, I'm going to condition on X10 equals A2.
P
5:53Percy LiangHOST
And if I run this, then I'm sampling from all the program traces.
Bayesian Networks 7 - Supervised Learning | Stanford CS221: AI (Autumn 2021)
P
1:56Percy LiangHOST
So we saw many ways of doing this, including manually by exhaustive enumeration, We can convert Bayesian networks into Markov networks and do Gibbs sampling.
P
2:07Percy LiangHOST
And then for HMMs, we have specialized techniques such as the forward-backward algorithm and particle filtering.
P
2:16Percy LiangHOST
So inference assumes that all these local conditional distributions are known.
P
2:21Percy LiangHOST
But the big question is, where do all of these come from? So all of these numbers are called the parameters of the Bayesian network, the red question marks.
Bayesian Networks 5 - Forward-backward Algorithm | Stanford CS221: AI (Autumn 2021)
P
20:04Percy LiangHOST
0.61 and 0.3. All right, so
P
20:13Percy LiangHOST
to summarize, we've presented the forward-backward algorithm for probabilistic inference in HMMs, in particular answering smoothing questions.
P
20:22Percy LiangHOST
So the key idea behind the forward background algorithm is this lattice representations, which allows us to compactly represent paths as assignments and the weights of each assignment to be the product of the edge weights.
P
20:40Percy LiangHOST
That allows us to define a dynamic program, which computes the forward and backward messages in an efficient way.
Bayesian Networks 1 - Overview | Stanford CS221: AI (Autumn 2021)
P
11:21Percy LiangHOST
We're actually going to reduce the problem in Bayesian networks to the same problem of probabilistic inference in Markov networks, allowing to leverage the stuff that we talked about when we talked about Markov networks.
P
11:36Percy LiangHOST
Then we're going to specialize to hidden Markov models, HMMs, an important special case of Bayesian networks.
P
11:42Percy LiangHOST
We're going to show that the forward-backward algorithm can leverage the chain structure of an HMM allowing you to do exact probabilistic inference efficiently, then
S
11:53speaker_0ADVERTISER
Hey, Spotify listeners.
1 more episode mentions Hidden Markov model.
Create an account to see the whole feed, search across every transcript, and follow the entities you care about.