Anand Gopalakrishnan
@agopal42.bsky.social
Postdoc at Harvard with @yilundu.bsky.social and @gershbrain.bsky.social PhD from IDSIA with Jürgen Schmidhuber. Previously: Apple MLR, Amazon AWS AI Lab. 7\.
agopal42.github.io
agopal42.github.io
Pinned
Excited to present "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery" at #NeurIPS2024! Poster: #3707 4:30pm on Thursday.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.
Reposted by Anand Gopalakrishnan
Goal selection through the lens of subjective functions:
arxiv.org/abs/2512.15948
I welcome any feedback on these preliminary ideas.
arxiv.org/abs/2512.15948
I welcome any feedback on these preliminary ideas.
Subjective functions
Where do objective functions come from? How do we select what goals to pursue? Human intelligence is adept at synthesizing new objective functions on the fly. How does this work, and can we endow arti...
arxiv.org
December 19, 2025 at 3:15 AM
Goal selection through the lens of subjective functions:
arxiv.org/abs/2512.15948
I welcome any feedback on these preliminary ideas.
arxiv.org/abs/2512.15948
I welcome any feedback on these preliminary ideas.
Excited to present "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery" at #NeurIPS2024! Poster: #3707 4:30pm on Thursday.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.
December 4, 2024 at 6:49 PM
Excited to present "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery" at #NeurIPS2024! Poster: #3707 4:30pm on Thursday.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.
TL;DR: Our model, SynCx, greatly simplifies the inductive biases and training procedures of current state-of-the-art synchrony models. Thread 👇 1/x.