paper-with-me

Papers

Interpretable Latent Spaces for Learning from Demonstration

2018-07-17 · Yordan Hristov, Alex Lascarides, Subramanian Ramamoorthy

Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in a corresponding high-dimensional sensory input stream from the world. Models such as deep neural networks, with high capacity through their large parameter spaces, can be used to compress the high-dimensional sensory data to lower dimensional representations. These low-dimensional representations facilitate symbol grounding, but may not guarantee that the representation would be human-interpretable. We propose a method which utilises the grouping of user-defined symbols and their corresponding sensory observations in order to align the learnt compressed latent representation with the semantic notions contained in the abstract labels. We demonstrate this through experiments with both simulated and real-world object data, showing that such alignment can be achieved in a process of physical symbol grounding.

📄 PDF Abstract BibTeX arXiv:1807.06583

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces

2020-06-02 · CVPR 2021 1 · Miguel Jaques, Michael Burke, Timothy Hospedales

Learning low-dimensional latent state space dynamics models has been a powerful paradigm for enabling vision-based planning and learning for control. We introduce a latent dynamics learning framework that is uniquely des…

Behavioural cloningImitation Learning

InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations

2017-03-26 · NeurIPS 2017 12 · Yunzhu Li, Jiaming Song, Stefano Ermon

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are…

Imitation Learning

Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

2024-10-27 · Mohammad Hassan Vali, Tom Bäckström

Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable …

Data AugmentationQuantization

Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods

2022-07-20 · Julian Schön, Raghavendra Selvan, Jens Petersen

Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semanticall…

Medical Image Analysis

Unsupervised Discovery of Interpretable Latent Manipulations in Language VAEs

2021-01-01 · Max Ryabinin, Artem Babenko, Elena Voita

Language generation models are attracting more and more attention due to their constantly increasing quality and remarkable generation results. State-of-the-art NLG models like BART/T5/GPT-3 do not have latent spaces, th…

SentenceText Generation