no code implementations • 5 Apr 2024 • Scott Ettinger, Kratarth Goel, Avikalp Srivastava, Rami Al-Rfou
These experiments demonstrate distillation from ensembles as an effective method for improving accuracy of predictive models for robotic systems with limited compute budgets.
2 code implementations • 12 Jul 2022 • Nigamaa Nayakanti, Rami Al-Rfou, Aurick Zhou, Kratarth Goel, Khaled S. Refaat, Benjamin Sapp
In this paper, we present Wayformer, a family of attention based architectures for motion forecasting that are simple and homogeneous.
Ranked #6 on Motion Forecasting on Argoverse CVPR 2020
no code implementations • CVPR 2016 • Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, Silvio Savarese
Different from the conventional LSTM, we share the information between multiple LSTMs through a new pooling layer.
Ranked #1 on Trajectory Prediction on Stanford Drone (FDE(8/12) @K=5 metric)
5 code implementations • NeurIPS 2015 • Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron Courville, Yoshua Bengio
In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder.
no code implementations • 26 Dec 2014 • Kratarth Goel, Raunaq Vohra, J. K. Sahoo
In this paper, we propose a generic technique to model temporal dependencies and sequences using a combination of a recurrent neural network and a Deep Belief Network.
no code implementations • 26 Dec 2014 • Kratarth Goel, Raunaq Vohra, Ainesh Bakshi
This paper presents a versatile technique for the purpose of feature selection and extraction - Class Dependent Features (CDFs).
no code implementations • 18 Dec 2014 • Kratarth Goel, Raunaq Vohra
Since the advent of deep learning, it has been used to solve various problems using many different architectures.