From philosophy to POMDPs to reinforcement learning & hierarchical planning to the publishing model in academia, I really enjoyed this conversation with Leslie.
Sorry Lex, I admit to having misspelled your name when telling people about your channel -- but I won't do it again ;-) Thanks for your efforts and interviews!
Rating: 6.7/10 In Short: Short and (kinda) sweet Notes: Leslie seemed nice and kind, but this made for a bit of a soft and gentle type of computer science interview that I felt lacked in excitement, motivation, and purpose. Lex had leslie jump around from specfiic topic to specific topic, which left me a bit confused and disoriented as a non comp sci person. But I am a scientist, and I still had a hard time following this in any story like fashion. Rather, it felt more like a laundry list of questions that lex asked and leslie answering them somewhat robotically. Would have liked a bit more background and then ease into depth to make topics and stories to give leslie a more personable feel.
Begins with a GEB mention, eloquently articulates issues I have been trying to categorise for years, is pro open access, isn't getting distracted by ill-formed big ideas... anything this person has ever said or written is now priority reading for me. Genius.
Being someone whose work environment is not alongside other programmers where I have to either use lay terminology or keep to myself with descriptions of what I do, it's intriguing and almost refreshing to hear conversations on this podcast constantly referring to everyday life in terms of functions, problem spaces, sets, and the like. really enjoying it.
Leslie is one those amazing guests who do not proffer opinions on supposedly deep questions, but are very lucid in what they do say. I really liked her!
3rd yr undergrad student. Learning ai on his own. I could understand the problem statements for deep learning and computer vision(couldn't solve them , obviously) , but not so much in reinforcement learning. This really helped. Reinforcement learning isn't just a computation problem. It's a merging of the disciplines mentioned under symbolic systems . One can specialize in one or more of thosw fields, but to make things work, all those perspectives are needed. Thanks for this.
Any person who doesn't value competition based on 'personal feelings' loses a lot of credibility. Its better than resenting it for ideological reasons, but its our most general method, and possibly most fundamental method of finding truth. Dismiss it at your peril.
I think the output we want from a "perception" system is a cost or a credit of the current state of the world. Just like we do in inverse reinforcement learning or target propagation for the credit assignement problem. Awesome video btw !
From philosophy to POMDPs to reinforcement learning & hierarchical planning to the publishing model in academia, I really enjoyed this conversation with Leslie.
Sorry Lex, I admit to having misspelled your name when telling people about your channel -- but I won't do it again ;-) Thanks for your efforts and interviews!
Like this lady. A free thinker who doesn't care for competition and care for investing into hard problems
Leslie is so eloquent, I think this is my favorite interview from the podcast
Thanks for this podcast
Thank you so much for this, Lex. Much love...
I was just following Leslie's MIT OCW course and thinking what a great teacher she is. I then find this! So excited to listen now.
Same here
She's great. I hold almost exactly the same opinions, but I am much worse at articulating them.
You know Listening to her made me think that humans are amazing !! really
Wow Leslie is smart as heck!
Rating: 6.7/10
In Short: Short and (kinda) sweet
Notes: Leslie seemed nice and kind, but this made for a bit of a soft and gentle type of computer science interview that I felt lacked in excitement, motivation, and purpose. Lex had leslie jump around from specfiic topic to specific topic, which left me a bit confused and disoriented as a non comp sci person. But I am a scientist, and I still had a hard time following this in any story like fashion. Rather, it felt more like a laundry list of questions that lex asked and leslie answering them somewhat robotically. Would have liked a bit more background and then ease into depth to make topics and stories to give leslie a more personable feel.
It will take a surprising amount of time to walk through Kuala Lumpur airport
wow!!...very knowledgeable...
@lex can you please add the outline back for videos?
What a great conversation.
Liked her AI perspective.
Begins with a GEB mention, eloquently articulates issues I have been trying to categorise for years, is pro open access, isn't getting distracted by ill-formed big ideas... anything this person has ever said or written is now priority reading for me. Genius.
Being someone whose work environment is not alongside other programmers where I have to either use lay terminology or keep to myself with descriptions of what I do, it's intriguing and almost refreshing to hear conversations on this podcast constantly referring to everyday life in terms of functions, problem spaces, sets, and the like.
really enjoying it.
Right?!
It's literally a different language and I perfer it.
How to create your own deep learning library?
Rock out! Nice love it !
Mind-opening
Great conversation!
Leslie is one those amazing guests who do not proffer opinions on supposedly deep questions, but are very lucid in what they do say. I really liked her!
3rd yr undergrad student. Learning ai on his own. I could understand the problem statements for deep learning and computer vision(couldn't solve them , obviously) , but not so much in reinforcement learning. This really helped. Reinforcement learning isn't just a computation problem. It's a merging of the disciplines mentioned under symbolic systems . One can specialize in one or more of thosw fields, but to make things work, all those perspectives are needed. Thanks for this.
Lex without his blazer is quite an experience
Great channel thank you
Any person who doesn't value competition based on 'personal feelings' loses a lot of credibility. Its better than resenting it for ideological reasons, but its our most general method, and possibly most fundamental method of finding truth. Dismiss it at your peril.
Glad to see a few women in this field. 😍
I really like the way she.....Talks?
interesting talk
I think the output we want from a "perception" system is a cost or a credit of the current state of the world. Just like we do in inverse reinforcement learning or target propagation for the credit assignement problem. Awesome video btw !
"paper is not required for prestige, as it turns out." sums up todays colleges/universities.
What did she read that makes her interested in computer science?
She sounds, and kind of looks like Judith Butler :D
It would be great to see Jeff Hawkins on Your podcast.
Here @ 2278; views..... ...... ......
Who is the author mentioned at 0:45?
en.wikipedia.org/wiki/G%C3%B6del,_Escher,_Bach
Anyone find the intro just a bit creepy?
Feels like listening to AMSR
Third