Search Results for author: Anand Gopalakrishnan

Found 9 papers, 7 papers with code

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning

no code implementations14 Oct 2024 Etai Littwin, Vimal Thilak, Anand Gopalakrishnan

We condition the target encoder and context encoder modules in IJEPA with positions of context and target windows respectively.

Image Classification Representation Learning

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

1 code implementation27 May 2024 Anand Gopalakrishnan, Aleksandar Stanić, Jürgen Schmidhuber, Michael Curtis Mozer

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures.

Object Object Discovery

Unsupervised Musical Object Discovery from Audio

1 code implementation13 Nov 2023 Joonsu Gha, Vincent Herrmann, Benjamin Grewe, Jürgen Schmidhuber, Anand Gopalakrishnan

Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition.

Object Object Discovery +1

Exploring the Promise and Limits of Real-Time Recurrent Learning

1 code implementation30 May 2023 Kazuki Irie, Anand Gopalakrishnan, Jürgen Schmidhuber

To scale to such challenging tasks, we focus on certain well-known neural architectures with element-wise recurrence, allowing for tractable RTRL without approximation.

Unsupervised Learning of Temporal Abstractions with Slot-based Transformers

1 code implementation25 Mar 2022 Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber, Sjoerd van Steenkiste

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems.

Decision Making

A Neural Temporal Model for Human Motion Prediction

1 code implementation CVPR 2019 Anand Gopalakrishnan, Ankur Mali, Dan Kifer, C. Lee Giles, Alexander G. Ororbia

We propose novel neural temporal models for predicting and synthesizing human motion, achieving state-of-the-art in modeling long-term motion trajectories while being competitive with prior work in short-term prediction and requiring significantly less computation.

Human motion prediction model +3

Cannot find the paper you are looking for? You can Submit a new open access paper.