BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//sebbo.net//ical-generator//EN
URL:https://lectures.london/imperial-college/beyond-bits-information-theor
 y-in-the-age-of-intelligent-machines/calender.ics
NAME:Lectures London
X-WR-CALNAME:Lectures London
TIMEZONE-ID:Europe/London
X-WR-TIMEZONE:Europe/London
BEGIN:VEVENT
UID:a57993e3-a0a9-41b9-a179-215af45042ff
SEQUENCE:0
DTSTAMP:20261106T132741
DTSTART:20261111T173000
DTEND:20261111T183000
SUMMARY:Beyond bits: information theory in the age of intelligent machines
LOCATION:Imperial College: Lecture theatre 200\, City and Guilds Building
DESCRIPTION:The ‘bit’ transformed how we compress\, transmit and store
  information. But as more information is produced by machines\, for machin
 es\, do the same rules still apply?\nProfessor Deniz Gündüz\, Professor 
 in Information Processing\, explores how information theory can help answe
 r questions emerging in the age of intelligent machines. \nPlease register
  to attend in person. A live stream link for online attendance is availabl
 e here.  \nWe look forward to seeing you on Wednesday 11 November!\nImpe
 rial Inaugurals are term-time lectures that celebrate our newest profess
 ors\, recognising their academic journey and showcasing their research.\nA
 bstract\n\nIn 1948\, Claude Shannon established a mathematical theory for 
 modelling and quantifying information: how much a source can be compressed
 \, and how much of it a noisy channel can carry. Those limits turned commu
 nication from a craft into a science\, and everything digital: the Interne
 t\, mobile telephony\, data storage\, has since been built around them. Sh
 annon also gave us the ‘bit’: common currency of the information age\,
  which let compression\, transmission\, computation and security be trea
 ted as four separate problems\, solved by different engineers. \nSoon\, m
 ost of the information crossing our networks will be produced by intellige
 nt machines\, for other intelligent machines. How will billions of them co
 mmunicate with each other: must they agree on a language in advance\, or c
 an they learn one? And do those old boundaries still make sense\, when a n
 etwork can compute\, a compressor can learn\, and the whole chain from sen
 sor to decision can be trained as one? \n\nBiography\nDeniz Gündüz is P
 rofessor of Information Processing at Imperial College London\, where he l
 eads the Information Processing and Communications Lab. In his inaugural l
 ecture he will argue that information theory is still the right instrument
  for answering such questions\, drawing on his group’s work on machines 
 that learn their own codes and protocols\; private and secure computation\
 , in which machines compute together without revealing what they hold\; wi
 reless image and video transmission that degrades gracefully rather than f
 ailing outright\; and compression by neural networks that learn from a sin
 gle signal. He will close on the question behind all of it: how far does i
 nformation theory reach into an age of intelligent machines?
URL;VALUE=URI:https://www.imperial.ac.uk/events/212280/beyond-bits-informa
 tion-theory-in-the-age-of-intelligent-machines/
END:VEVENT
END:VCALENDAR