5 Burst results for "Katherine Foreman"

"katherine foreman" Discussed on Talking Machines

Talking Machines

11:46 min | 2 months ago

"katherine foreman" Discussed on Talking Machines

"To talking machines. I'm Katherine Foreman and I'm neal learns and today we are bringing you breaking our format. Our usual format our new usual format a little bit kneel at we have the opportunity to sit down with the General Chair and senior program chair or this year's interruption of the international conference on learning representations I clear which was entirely virtual this year Alexander Rush of Cornell and Shakira Muhammad of deep. Mind thank you so much for joining us today. I really appreciate it off. Excellent Catherine great to be here. I'd love to do a little bit of background on. I clear I just sort of like mainly to give us a sort of a context for the conference in in the ecosystem of other conferences. WanNa know how did the conference get to where it is today? Yes thank you neil. That sounds like a very good question. How the conference get to where it is today. This year was already breaking ground. It was going to be taking place in Ethiopia which I think is the first time any of the large conferences have been held on the African continent But then all of a sudden we had this massive global change and it was decided that the conference would take place entirely. Virtually so Sasha. I'd love to hear from you a little bit more about how you see. I clear fitting into the larger system of conferences. And what your experience with. It's been and how this change took place shore so this was the eighth international conference of learning representations but it was run as a workshop for several years so it started in two thousand thirteen. And I think what's remarkable about the conference it's been experiencing exponential growth for the last basically for its entire history and so it's a conference where everyone is kind of a newcomer each year. We have most people kind of experiencing it for their first time. I think personally I didn't really attend. I clear till about three or four years ago and I was coming from it from the natural language processing community so conferences like ACL P that she makes up a relatively large part of kind of this multi disciplinary area. It's a conference. That kind of welcomes a large group of people doing different forms of representation learning and deep learning and things of that form I think it differs from some of the other machine learning conferences in that. It's a bit more experimental. I think a lot of people know it for its experimental reviewing format and for the structure of how it's laid out and I think one of the reasons it was so interesting to work on is because it's a conference that kind of allows for more experimentation in its format in its structure and we took that to heart in both the venue this year and also in kind of change to the virtual conference format. So this sort of like the experimental stuff it does on its own. It was the first to open reviewing. And then there's the experimental stuff that's forced upon it so. I find so amazing. What you had to do this year is first of all you were taking a major conference to the African continent for the first time which was a major undertaking in itself. And then you had to cancel the first major conference on the African continent. Tell us how how I don't know who's best to sort of speak to that. She cared. Do you want to tell us how that came about? And how you reacted yes. I think we were actually quite far along in our work dealing with the European conference it was going to be in a great venue in the Millennium Hall. Very close to the airport in Ethiopia. Lots of things have been set up. Even down to the whole Shedu of the conference itself was set up. The we're going be three. Parallel tracks experimented the conference in that way. All the keynotes. All the speaking. The setup of the post is all of these kinds of things are done and then it was a difficult time the end of February the beginning of March when it was very clear that the long run of cove it and would come into effect and a lot of consideration and debate with many many different kinds of people around actually cancelling the conference. But I think in the end You know it was obviously a good decision. Forced us to experiment in the new way so I was pretty happy with the with the end to actually get to do it. So what was the thing that Chicago pops happiest about about the way the conference went the thing that surprised you the most because I know both of you I mean it must be in so much stress. Just organizing a major conference like this is like major stress in in the base case and then organizing one where you have to reorganize the entire conference within the space of a few weeks. I just can't imagine it but let's start with the positive things and and pats that recession. Say She Sasha. What was the thing that you most pleasantly surprised about about the conference? Yeah so there. I think there were a lot of things that kind of were unexpected or kind of emergent behavior. That came up during the conference itself. The part that I think I spent the most time on and was most excited about was the the social interactions particularly chat and the socials. That emerged I think that was the part we were most worried about. It's the part I get the most out of conferences talking to experts in the field kind of having conversations that you didn't expect or learning about papers that you didn't know that we're coming. We really built that around kind of slack. Like chat experience and seeing the different topic rooms emerged. There was a very interesting created. A I room. That came out of nowhere. The community had several very interesting events. That were just so neat to attend and then we also ran several mentoring sessions just kind of out of nowhere in the middle of the conference that were super interesting and kind of almost better than I would have imagined. That could have occurred. Say getting a drink at a bar at an normal conference that that's really interesting social PA which is good almost thing. That's one of the toughest bitch I guess it's just a different type of social experience and of course everyone's sort of locked away anyway so any social. It's Great Care. How was also the social part yet pleasantly surprised there were so many things I think from. Just the ability to engage with our speaking usually gets a keynote speaker comes up to the stage. They end their talk. You get this one question very quickly and everyone has to rush off to the next to the next talk to the next poster session but here. We actually got to have a very long meaningful conversation with our keynote speakers. Very much. Like this kind of podcasts. We get to take questions off the CIA. Take Life questions really getting engaged. Go Bit more deeply by the thing that I found. Most surprising was maybe to pick up on the experimental nature of the conference. In the virtual format. The conference itself becomes the new kind of environment in which you can experiment and play in and particularly for us. We use a lot of machine learning tools in the design of the conference in the reviewing process. We had some late unbearable models that we use to do calibration of scores. The natural language tool I can tell you a lot. More than does the visualization and the recommendation. We actually do have recommended system in the back and their questions are on fairness of the recommended recommendations that we are given that they Equally every paper is represented. And so I think is really something powerful about virtual conference that now. Our own conferences an environment in which we can play and redeploy the work. That's actually presented the conference. I thought that was for me. Pretty something special. I don't want to say almost kind of like saying it was like second life with a purpose rather than so secure. I'd love to dig in more on those tools a little bit because I think one of the things that a lot of conferences and a lot of in person gatherings these days or just thinking about is like okay. Well a virtual meeting is just one where everybody gets on zoom now and we just do the same thing but we do it as far apart from each other as we possibly can but you guys spent the time to create all these tools that she. I think you were mentioning when you're talking about the sort of like eating your own dog food process that use a lot of ai to create the conference for curator information organizing things exploring the the papers that you had. Can you tell me and I believe and this is the room. That's going around that. Sasha insecure you guys made a lot of those yourselves right. Can you tell me a little bit about the process of making those and like how you decided that these were needed? How did you go from okay? We can't go to Ethiopia so we'll have the the world's largest zoom call to thinking about curate this information in a way that's going to be more efficacious in a in a digital environment. How did you make those curatorial choices for me? I think what we designed the conference we had we. We actually met for six weeks three days a week. Five thirty PM UK tie For the entire time and there were two principles we use. The design of conference and one of them was that we needed to be accessible and the other one was to be inclusive. And so everything was designed around these. Two kinds of principals and inclusion meant it needed to be worldwide global. So it doesn't matter if you're in Sydney or in Lima in Johannesburg or London. The conference should not force you to work at a bizarre. Our and one of the things we want to do is healthy working hours favor on whether or not your parent. The covert crisis means that you cannot do certain things recovering. You could create a flow of activities. Whenever you could. You could skip today. Go to Thursday comeback to today and so that was really an many tools make things certainly inclusive Because of them you know there are certain questions around. Accessibility captioning mobility. That don't need to be question. We can talk about some of the disadvantages of this on and then cost was another issue. We often talk about visas. Cost Travel Hotel expenses. All of these sort of go away and then inactive I think Sasha mentioned earlier on the social element that we really wanted that to be trying to recreate to the extent that we could that bumping into the corridor to be introduced by someone else to have kind of self organizing ability to chat everywhere and speak to everyone at anytime so these were the two and whenever we face a very difficult situation where we needed to make a decision or tweaking. The design of the website. We would come back to these two principles. Do they support inclusion? Do they support accessibility and then simplified our decision-making also because we only had six weeks? Yeah so in terms of actual tools. We use so about three weeks before the conference. It became clear that we have a lot of ideas but that it would be very hard to find someone that we could kind of pay to implement them. I have a very close collaborator Hendrix. Robots and we worked for the last several years on visuals -ation methods for understanding a systems. So we have several collaborations on that front. And he mentioned that a couple years ago he built a tool for document visualization and that he was very interested in revisiting. Some of these questions in kind of a world where we have. Ai Methods supporting them and so it seemed like a great opportunity for collaboration and we were both quarantine so we thought we would try it out and so we decided we were just going to go forward and build what we could We started with kind of a design that we wanted as much kind of browsing as possible that we wanted to have some search but really we wanted to kind of have the experience that you're walking around conference looking for what's cool and kind of seeing. What's there so all our tools kind of build in kind of randomness? I A lot of kind of exploratory. Visualizations things of that form and then we also thought it would be fun to utilize a bunch of AI tools to make this possible one tool we used was a.

Sasha Ethiopia Millennium Hall Catherine Wan Katherine Foreman Chicago Shakira Muhammad Alexander Rush General Chair CIA Cornell UK neal Hendrix program chair Sydney London
ICLR: accessible, inclusive, virtual

Talking Machines

05:53 min | 2 months ago

ICLR: accessible, inclusive, virtual

"I'm Katherine Foreman and I'm neal learns and today we are bringing you breaking our format. Our usual format our new usual format a little bit kneel at we have the opportunity to sit down with the General Chair and senior program chair or this year's interruption of the international conference on learning representations I clear which was entirely virtual this year Alexander Rush of Cornell and Shakira Muhammad of deep. Mind thank you so much for joining us today. I really appreciate it off. Excellent Catherine great to be here. I'd love to do a little bit of background on. I clear I just sort of like mainly to give us a sort of a context for the conference in in the ecosystem of other conferences. WanNa know how did the conference get to where it is today? Yes thank you neil. That sounds like a very good question. How the conference get to where it is today. This year was already breaking ground. It was going to be taking place in Ethiopia which I think is the first time any of the large conferences have been held on the African continent But then all of a sudden we had this massive global change and it was decided that the conference would take place entirely. Virtually so Sasha. I'd love to hear from you a little bit more about how you see. I clear fitting into the larger system of conferences. And what your experience with. It's been and how this change took place shore so this was the eighth international conference of learning representations but it was run as a workshop for several years so it started in two thousand thirteen. And I think what's remarkable about the conference it's been experiencing exponential growth for the last basically for its entire history and so it's a conference where everyone is kind of a newcomer each year. We have most people kind of experiencing it for their first time. I think personally I didn't really attend. I clear till about three or four years ago and I was coming from it from the natural language processing community so conferences like ACL P that she makes up a relatively large part of kind of this multi disciplinary area. It's a conference. That kind of welcomes a large group of people doing different forms of representation learning and deep learning and things of that form I think it differs from some of the other machine learning conferences in that. It's a bit more experimental. I think a lot of people know it for its experimental reviewing format and for the structure of how it's laid out and I think one of the reasons it was so interesting to work on is because it's a conference that kind of allows for more experimentation in its format in its structure and we took that to heart in both the venue this year and also in kind of change to the virtual conference format. So this sort of like the experimental stuff it does on its own. It was the first to open reviewing. And then there's the experimental stuff that's forced upon it so. I find so amazing. What you had to do this year is first of all you were taking a major conference to the African continent for the first time which was a major undertaking in itself. And then you had to cancel the first major conference on the African continent. Tell us how how I don't know who's best to sort of speak to that. She cared. Do you want to tell us how that came about? And how you reacted yes. I think we were actually quite far along in our work dealing with the European conference it was going to be in a great venue in the Millennium Hall. Very close to the airport in Ethiopia. Lots of things have been set up. Even down to the whole Shedu of the conference itself was set up. The we're going be three. Parallel tracks experimented the conference in that way. All the keynotes. All the speaking. The setup of the post is all of these kinds of things are done and then it was a difficult time the end of February the beginning of March when it was very clear that the long run of cove it and would come into effect and a lot of consideration and debate with many many different kinds of people around actually cancelling the conference. But I think in the end You know it was obviously a good decision. Forced us to experiment in the new way so I was pretty happy with the with the end to actually get to do it. So what was the thing that Chicago pops happiest about about the way the conference went the thing that surprised you the most because I know both of you I mean it must be in so much stress. Just organizing a major conference like this is like major stress in in the base case and then organizing one where you have to reorganize the entire conference within the space of a few weeks. I just can't imagine it but let's start with the positive things and and pats that recession. Say She Sasha. What was the thing that you most pleasantly surprised about about the conference? Yeah so there. I think there were a lot of things that kind of were unexpected or kind of emergent behavior. That came up during the conference itself. The part that I think I spent the most time on and was most excited about was the the social interactions particularly chat and the socials. That emerged I think that was the part we were most worried about. It's the part I get the most out of conferences talking to experts in the field kind of having conversations that you didn't expect or learning about papers that you didn't know that we're coming. We really built that around kind of slack. Like chat experience and seeing the different topic rooms emerged. There was a very interesting created. A I room. That came out of nowhere. The community had several very interesting events. That were just so neat to attend and then we also ran several mentoring sessions just kind of out of nowhere in the middle of the conference that were super interesting and kind of almost better than I would have imagined. That could have occurred. Say getting a drink at a bar at an normal conference

Ethiopia Sasha Katherine Foreman Catherine Shakira Muhammad Millennium Hall General Chair Cornell Alexander Rush Chicago Program Chair Neal WAN
"katherine foreman" Discussed on Talking Machines

Talking Machines

03:42 min | 1 year ago

"katherine foreman" Discussed on Talking Machines

"You are listening to talking machines. I'm Katherine foreman. And I'm Neil Lawrence. And today Neil wanted to talk to you about something pretty specific that I'm hoping you'd walk you through five papers for Mike tipping, which to me. Just sounds like a really great New Yorker short story. But I don't think it's that. No. So what this is about five years ago? So it's everything's in fives. Today, I was down in Cambridge at the time. I was based in Sheffield, and I had dinner with Mike tipping and David Dino, and Mike is an amazing for such a who was opposed talk. When I was a student, and I love he worked on things like the relevance vector machine. He worked telling them mixed his of publicity PCA and public. He derived the maximum likelihood solution for that really really elegant work, but he sort of went into industry for number of years back in the day before it was cool to be. I mean, it was on cool. But for everyone. Now, he was like hipster industry. You know, it's sort of like in you know, he was like early there and industry being hipster about it. And then, but he's back now, he's a which is great for academia, he's actually because he's type of hip stuff. He's now out of industry and at the university of buff. He's teaching again, he teaches really really well his great material. But he asked me he said, I guess at the time he was still in industry and wasn't. I don't think he he mentioned to me that evening. He said if I were to read five papers from the last couple of years that captured the interesting potent stuff happening in MO, what would they be? And so I was thinking about that the other day, I was thinking I would find it a lot harder to give someone five papers today. And I don't know if that says something about meal the field will the like number of papers. Well, just to cover the interesting things going on at MLS s. In Stellenbosch, Sebastian Nova, sit in was talking about Gant's, and he was showing how many gone papers were being published a month. And there was a number so large. I don't even want to say because it just seems can't be right per month. Like some night three hundred sixty Gan papers were being published on I guess, so you know, it's kind of a bit hard. So obviously, you would probably mentioned the Gan paper as one that people should be reading. Yes. The five that I mentioned then were statistic variation inference by Hoffman Wang blind paisley. And I think that that is that's a really to me that's been a massively important method. So that's sort of people using it very widely. Now, I think that was a good call because it's a way of doing approximate busy and inference problematic models, but potentially billions of data, and she I think going back to that time we organized a workshop put Europe's the year when Mark Zuckerberg turned up probably was. Two thousand thirteen year we had like a Maxwell, and as well because the next paper is authority and MC MCI land, cutting metropolis Hastings budget by karate Kara Chen and welling by think, I could also mentioned papers by max and UI in that space, these approaches so these these two papers sort of related the first one is about how you're scaling up variation infants for very large data, and I think in particular David Blythe had an interest in doing that. I it of these language waddles L, D A and so forth. And I'm think we're seeing a comeback a little bit for those types of models in the Beijing non parametric workshop at last year's Europe's was was a was a big workshop which I couldn't attend..

Mike tipping Neil Lawrence Europe Katherine foreman PCA Gant Mark Zuckerberg Gan MC MCI Cambridge Stellenbosch Beijing university of buff Hoffman Wang David Blythe Kara Chen Sheffield Maxwell Mike
"katherine foreman" Discussed on KGO 810

KGO 810

02:25 min | 3 years ago

"katherine foreman" Discussed on KGO 810

"Gene the us how old boy i said that was amazing that is katherine foreman who wrote that song is what i said you play an instrumental doj like this banging on the piano i write i write on guitar but i would not call myself akhtar okay you know it's funny i instrument jimmy what jimmy well as a horrible blair and he's not a great singer and the best songwriter and my generation i think that's that's great stuff you know in before you play this last song so the the what is it like out there this is a a real unique style music as you say honkytonk it's hell is keflavik country some blows in if i mean people here it i go i this is the most people just like it i just like what i here so it's outright we are recording at highstreet studios right now soon we'll have some that's always find like those those you know the what those mixing sessions said in a four in the morning and yeah right it is it it's even harder now that people don't do drugs was easier a way for bass player to fall asleep they can turn it down for this is his great stuff and you know it's funny the ice to play that blue note and you go down there and we had a data honky tonk night of these years ago when i was young kid and you go in there and and people that would show up in town and committed everybody's attracted to that sound you know if the rolling stones qatar league tarp but keith richards he leaves a huge honky tonk fan he has a collection i love those guys love the blues love country and you know you go back and i remember secured my dad was a cop any some as i've they were racists are there all racist okay but i remember charlie pride was like the first black country singer remember them saying well you know they're not all bad no you look back and you is that the country music brought a lot of people to rhythm and blues and to honky tong and then to rock and roll and that progression of people just keep your eyes ears and minds open it's amazing right all right so what is this last songchol is one of britain by.

katherine foreman doj blair highstreet studios keith richards britain akhtar jimmy honky tonk qatar charlie honky tong
"katherine foreman" Discussed on KGO 810

KGO 810

02:11 min | 3 years ago

"katherine foreman" Discussed on KGO 810

"He said the us how old boy i doubt it and that was amazing that is katherine foreman who wrote that song is what i said you play an instrumental does like this banging on the piano i wrote i write on guitar but i would not call myself qatar okay you know it's funny i jimmy what jimmy well a horrible player and he's not a great singer and the best songwriter my generation i think that's that's great stuff you know in before you play this last song so the the what is it like out there this is a a real unique style music as you say honky tonk goal is called flavor country some blues i'm in the people here at i go i just most people just like it just like what i hear so it's ever cd outright we are recording at highstreet studios right now soon we will have some that's always find like those those you know the what those mixing sessions said in a four in the morning an and inquiry yeah right it is it it's it's even harder now that people don't do drugs was easier a way flood base player to fall asleep they could turn it down for this is his great stuff at you know it's funny the used to play the blue note and you go down there and we had a data honkytonk night of this is years ago when i was young kid and you go in there and and people that would show up in town and committed everybody's attracted to that sound you know it in the rolling stones qatar league carplay keith richards he leaves a huge honky tonks van he has a collection of those guys love the blues of country and you know you go back and i remember secured my dad was a cop any some as as they were racists are they're all racist okay remember charlie pride was like the first black country singer remember them say well you know they're not all bad right no but you look back and it is this that the country music brought a lot.

katherine foreman highstreet studios qatar jimmy honky tonk qatar league keith richards charlie