You may have seen our tweet round-up from the first few days of the AAAI 35th conference on artificial intelligence. During the second part of the conference we've enjoyed further invited talks, interesting panel sessions, and workshops. In our second round-up, we collect tweets from Saturday 6 to Tuesday 9 February. I just had the joy of moderating a fascinating #AAAI2021 plenary talk by @prfsanjeevarora, "Opening the Black Box of Deep Learning". People are actually starting to understand dynamics of gradient descent; GANs; generalization; why LMs work.

In September 2020, Regina Barzilay was announced as the winner of the inaugural AAAI Squirrel AI award. Regina was formally presented with the prize during an award ceremony at the AAAI2021 conference, following which she delivered an invited talk. She spoke about two particular areas of medicine that she has been researching: drug discovery and cancer diagnosis. It is well-known that the development of drugs is slow and expensive. Currently, drug discovery is primarily experimentally driven, with properties of molecules investigated empirically.

The AAAI 35th conference on artificial intelligence started on 2 February. So far, we've been treated to some excellent invited talks, tutorial sessions, and diversity and inclusion events. The poster sessions are also now in full swing. Here is our round-up of the first few days of the conference as seen by the Twitter-sphere. Excited to share the best paper awards for #AAAI2021.

The 35th AAAI Conference on Artificial Intelligence (AAAI2021) starts on Tuesday 2 February and runs until Tuesday 9 February. Find out about some of the main events that are taking place throughout the virtual conference. AAAI have announced the following distinguished invited speakers at this year's conference. Tuomas Sandholm (Carnegie Mellon University, Optimized Markets, Inc., Strategy Robot, Inc., Strategic Machine, Inc.) Title to be confirmed These events take place throughout the week. Click on the links to find out more details about each event.