XAI-SA 2024, Opening talk
Summary
TLDRThis workshop delves into explainable machine learning and AI, addressing the shift from interpretable models to the black box nature of deep learning. It aims to make these models transparent through post-training interpretation methods or by designing inherently interpretable models. The event features presentations on various topics, including spectrum interpretability in music machine learning, hybrid deep neural audio processing, and the challenges of understanding AI models. With 20 paper presentations, oral talks, and a panel discussion, the workshop fosters collaboration and innovative ideas in the field of explainable AI.
Takeaways
- 📘 The workshop is focused on explainable machine learning and AI, which has become a prominent field due to the rise of deep learning and the resulting black box models.
- 🔍 Explainable machine learning aims to make these complex models transparent, allowing for better understanding of their decision-making processes.
- 🛠️ There are various solutions to achieve explainability, including post hoc interpretation methods and designing inherently interpretable models from the start.
- 📈 The trade-offs between these methods will be explored during the workshop, with presentations and discussions on the latest research and applications.
- 🎓 The workshop features invited talks from experts in the field, including researchers from the speech and audio community and a renowned machine learning expert.
- 📚 There will be 20 paper presentations, with four oral presentations and 16 poster presentations, covering a range of topics from model interpretation to application-specific uses.
- 🎼 Specific applications discussed include music machine learning, speech and audio processing, and analysis of deep learning models for various purposes.
- 🗓️ The workshop schedule includes a series of talks, paper presentations, and a panel discussion aimed at fostering collaboration and generating new ideas.
- 📹 The event is being recorded, and there is a YouTube channel for the workshop where invited talks and author videos will be posted.
- 👥 The organizers and reviewers are acknowledged for their efforts in ensuring a thorough review process, with each paper receiving at least three reviews.
- 📝 Authors are encouraged to submit videos for their papers to the workshop's email for inclusion on the YouTube channel.
Q & A
What is the main focus of the workshop described in the transcript?
-The main focus of the workshop is on explainable machine learning and explainable AI, particularly in the context of deep learning models that are often considered black boxes.
Why has explainable machine learning become more important in recent years?
-Explainable machine learning has become more important due to the rise of deep learning, which has led to the creation of complex models that are not easily interpretable, thus making it a necessity to make these 'black box' models more transparent.
What are the two main approaches to making machine learning models more interpretable as mentioned in the transcript?
-The two main approaches are: 1) using post hoc interpretation methods where the original model is not altered but an attempt is made to understand its workings after training, and 2) designing an interpretable model from the start.
What is the trade-off that needs to be explored when choosing between the two approaches to explainability?
-The trade-off involves balancing the model's interpretability with its performance. Sometimes, more interpretable models may not perform as well as complex, less interpretable models.
What is the goal of the workshop in terms of the participants?
-The goal of the workshop is to bring together people working in the field of explainable AI to foster collaborations and come up with innovative ideas.
How many paper presentations are planned for the workshop?
-There are 20 paper presentations planned for the workshop, including four oral presentations.
What types of topics can be expected in the paper presentations and invited talks?
-The topics cover a range of areas including interpretable models, applications of post hoc explanation methods, analysis of deep learning models for music, and methodological approaches to explainable AI in speech and audio applications.
Who are some of the invited speakers mentioned in the transcript, and what are their areas of expertise?
-Some of the invited speakers include Ethan, who will talk about spectrum of interpretability for music machine learning; Cynthia Rudin from Duke University, who will discuss interpretable models versus post hoc interpretations; Professor G, who will cover hybrid and interpretable deep neural audio processing; and Gordon Wiinn, who will discuss understanding investigations into probing and training data memorization of AI models.
What is the schedule for the poster presentations at the workshop?
-The first poster session is at 10 AM, and presenters are asked to set up their posters by that time. All participants will present in all the sessions.
What is the role of the reviewers in the workshop, and how many reviews were written in total?
-The reviewers played a crucial role in the evaluation process, ensuring that each paper received at least three reviews, and in most cases, four. A total of 66 reviews were written for the workshop.
How can authors share their presentations or videos related to the workshop?
-Authors can share their videos by sending them to the workshop's email, and these will be featured on the workshop's YouTube channel, along with the invited talks.
Outlines
📚 Introduction to Explainable AI Workshop
The speaker begins by welcoming attendees to the workshop on explainable machine learning and AI, emphasizing the importance of making complex models more transparent. The session will cover various methods for interpreting machine learning models, including both post-hoc interpretation techniques and inherently interpretable models. The workshop aims to foster collaboration and generate new ideas, with presentations from invited speakers and contributions from various researchers. Attendees will explore the balance between model accuracy and interpretability, with examples provided throughout the day.
🎤 Workshop Structure and Presentations
The speaker outlines the workshop’s structure, mentioning the number of paper presentations, oral talks, and poster sessions. Various topics will be covered, including interpretable models, explainable AI methodologies, and specific applications in speech and audio. Invited speakers from prominent institutions will present on key areas such as music machine learning, neural audio processing, and AI model interpretability. The session will conclude with a panel discussion, encouraging audience interaction. Additionally, the speaker mentions logistical details, including the setup of posters, the role of reviewers, and the workshop’s YouTube channel for accessing recorded content.
Mindmap
Keywords
💡Explainable Machine Learning
💡Deep Learning
💡Black Box Models
💡Post Hoc Interpretation
💡Interpretable Models
💡Spectrogram
💡Invited Talks
💡Oral Presentations
💡Poster Presentations
💡Panel Discussion
💡YouTube Channel
Highlights
The workshop focuses on explainable machine learning and AI, addressing the shift from interpretable models to the need for transparency in deep learning black box models.
Explainable machine learning aims to make black box models transparent through post-training interpretation methods or by designing interpretable models from the start.
There is a trade-off between model accuracy and interpretability that will be explored in the workshop presentations.
The workshop will feature 20 paper presentations, including four oral presentations and a poster session, covering various aspects of explainable AI.
Submissions include research on interpretable models, post hoc explanation methods, and applications in speech and audio processing.
Invited speakers from the speech and audio community and a renowned machine learning researcher will provide talks on various topics related to explainable AI.
Ethan will discuss the spectrum of interpretability for music machine learning, emphasizing the importance of understanding model focus areas.
Cynthia Rudin from Duke University will compare interpretable models with post hoc interpretations, highlighting the challenges and benefits of each approach.
Professor Grishar will present on hybrid and interpretable deep neural audio processing, exploring new methods in audio analysis.
Gordon Wiinn from MER will delve into understanding investigations into AI model memorization of training data, a critical issue in AI ethics.
Professor Shinji Watanabe will discuss explainable speech foundation models, aiming to improve transparency in speech recognition systems.
Dr. Janel Pargman will present on using NMF for interpretable audio classification, showcasing a novel approach to making AI decisions clearer.
The workshop will conclude with a panel discussion featuring the invited speakers, encouraging interaction and idea generation among participants.
The schedule and details are available on the workshop website, with specific instructions for poster presenters on setup times and session formats.
The workshop has a YouTube channel where all invited talks and some author submissions will be uploaded for wider access.
The workshop organizers and reviewers are acknowledged for their efforts in ensuring a rigorous review process with 66 reviews in total.
The workshop is being recorded, and participants are reminded to be aware of the camera for a professional presentation.
Transcripts
right I think we'll get started um so
thanks a lot everyone for uh being here
uh 8:30 in the morning um so today it's
going to be about explainable machine
learning explainable AI we word like
machine learning AI intership
interchangeably in the title
um
so let me say uh what is explainable
machine learning so I guess few years
ago this wasn't like before deep
learning you happened uh this wasn't
really kind of like a feeli because
models were interpretable but like with
uh you know everything being deep
learning now uh the chances are that we
have blackbox models in what we do so
basically with explainable machine
learning what we try to do is to somehow
make these black boxes uh transparent
right there's different solutions like
we will see like uh today people will
talk about host HW interpretation
methods where um you don't touch the
original model but you do something else
after training to U uh understand what's
going on going on in in the model or you
could um uh just design an interpretable
model to begin with there's a trade-off
to explore uh so we will see see these I
guess in the presentations uh of the
invited talks today and
also uh there will be quite a few of
papers so you'll see that there also
here like I just like show for instance
uh how can we like what happens if you
have like a spectrogram input your
explainer kind of focus on a particular
area in this case it was like a chirp so
you see that maybe you cannot see
because the colors uh but like a with an
explain with the explanation methods we
are able to kind of like show where the
model is focusing on U but this Workshop
so explaining explainable AI is a
develop developing field right um and
basically this workshop's goal is to
bring together people who are working in
this field and hopefully you know like
uh Foster collaborations and uh uh come
up with some nice ideas hopefully at the
end of the day uh so today we will have
20 paper presentations uh there will be
four oral presentations and in total we
will have 20 posters so everybody will
do a poster presentation um I'll talk
more about the details but like uh we
had submissions on interpret
models about application of different
post talk explanation methods on various
various speech and audio applications we
had some papers on analysis of llms for
music and we also have some
methodological explainable AI
papers so um we also have invited
speakers from the speech and audio like
iasp community and also uh we have a
methodological machine learning talk uh
from a uh from a renowned XI researcher
uh um so with that uh we will start
today with Ethan we there uh he will
talk about um spectrum of
interpretability for music machine
learning then we will have Cynthia Rudin
Professor C Cynthia Ruden from Duke
University she will talk about um
interpretable models versus uh uh you
know post interpretations it will be
right after uh Ethan's talk then we will
have Professor G rishar from uh
telec comp part um it will be about
hybrid and interpretable deep neural
audio processing it will be after the
oral talks 11 15 then we will have
Gordon wiin from uh from mer there uh so
it will be about uh basically
understanding reg tating investigations
into probing and training data
memorization of AIO Genera models we had
one uh then we have Professor Shinji
vatan there it's about uh the talk is
about toward explainable speech
Foundation
models and then finally we will have Dr
Janel parik on using nmf uh for
interpretable audio classification this
will be the last talk and in the end at
the end of today we will have a panel
discussion with these wonderful
panelists and hopefully you know it will
be an interactive panel so that you know
uh you'll ask questions and and we'll
come up with ideas hopefully um so let
me exp so this is the
schedule uh you can find it on the
website uh but for the poster presenters
basically so the first poster session is
at 10 uh so we ask you to set up set up
your
poster uh at 10 um and basically
everybody will present in all the
sessions okay uh we'll probably remove
some of the
chairs back there so that that people
have more
space um and the organizers so myself
Jam suban Franchesco pan over there m
rali who's uh not here Shang gupa bcar
jman who's on Zoom uh and Paris I don't
know where Paris is is like back
on yeah um so uh these are our wonderful
reviewers um
basically we made we tried well each
paper had received received at least
three reviews and most in most cases we
had four reviews and uh in total 66
reviews were
written uh we thank to reviewers for
their
work and one last thing we have a
YouTube channel so for the authors uh if
you haven't sent your video yet please
send it to us on our Workshop
email um
yeah some of us some some of you already
did that like and it's on the on the
YouTube channel of the of the
workshop and we will uh we will put also
all the invited talks on the on our
YouTube
channel uh oh we are recording the uh
the event and there's like a camera so
uh make sure to smile and uh that's it
for me and uh we will continue with uh
Ethan so Franchesco will introduce Ethan
but maybe yeah Ethan maybe you can come
and you can set up everything
5.0 / 5 (0 votes)