Simple Mechanisms for Representing, Indexing and Manipulating Concepts
- URL: http://arxiv.org/abs/2310.12143v1
- Date: Wed, 18 Oct 2023 17:54:29 GMT
- Title: Simple Mechanisms for Representing, Indexing and Manipulating Concepts
- Authors: Yuanzhi Li, Raghu Meka, Rina Panigrahy, Kulin Shah
- Abstract summary: We will argue that learning a concept could be done by looking at its moment statistics matrix to generate a concrete representation or signature of that concept.
When the concepts are intersected', signatures of the concepts can be used to find a common theme across a number of related intersected' concepts.
- Score: 46.715152257557804
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep networks typically learn concepts via classifiers, which involves
setting up a model and training it via gradient descent to fit the
concept-labeled data. We will argue instead that learning a concept could be
done by looking at its moment statistics matrix to generate a concrete
representation or signature of that concept. These signatures can be used to
discover structure across the set of concepts and could recursively produce
higher-level concepts by learning this structure from those signatures. When
the concepts are `intersected', signatures of the concepts can be used to find
a common theme across a number of related `intersected' concepts. This process
could be used to keep a dictionary of concepts so that inputs could correctly
identify and be routed to the set of concepts involved in the (latent)
generation of the input.
Related papers
- Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks.
We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm.
Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
arXiv Detail & Related papers (2024-07-19T17:50:11Z) - Knowledge graphs for empirical concept retrieval [1.06378109904813]
Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user.
Here, we present a workflow for user-driven data collection in both text and image domains.
We test the retrieved concept datasets on two concept-based explainability methods, namely concept activation vectors (CAVs) and concept activation regions (CARs)
arXiv Detail & Related papers (2024-04-10T13:47:22Z) - Grounded learning for compositional vector semantics [1.4344589271451351]
This work proposes a way for compositional distributional semantics to be implemented within a spiking neural network architecture.
We also describe a means of training word representations using labelled images.
arXiv Detail & Related papers (2024-01-10T22:12:34Z) - CEIR: Concept-based Explainable Image Representation Learning [0.4198865250277024]
We introduce Concept-based Explainable Image Representation (CEIR) to derive high-quality representations without label dependency.
Our method exhibits state-of-the-art unsupervised clustering performance on benchmarks such as CIFAR10, CIFAR100, and STL10.
CEIR can seamlessly extract the related concept from open-world images without fine-tuning.
arXiv Detail & Related papers (2023-12-17T15:37:41Z) - A Recursive Bateson-Inspired Model for the Generation of Semantic Formal
Concepts from Spatial Sensory Data [77.34726150561087]
This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data.
The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept.
The model is able to produce fairly rich yet human-readable conceptual representations without training.
arXiv Detail & Related papers (2023-07-16T15:59:13Z) - ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and
Acquisition at Inference Time [49.067846763204564]
Humans have the remarkable ability to recognize and acquire novel visual concepts in a zero-shot manner.
We introduce Zero-shot Concept Recognition and Acquisition (ZeroC), a neuro-symbolic architecture that can recognize and acquire novel concepts in a zero-shot way.
arXiv Detail & Related papers (2022-06-30T06:24:45Z) - Automatic Concept Extraction for Concept Bottleneck-based Video
Classification [58.11884357803544]
We present an automatic Concept Discovery and Extraction module that rigorously composes a necessary and sufficient set of concept abstractions for concept-based video classification.
Our method elicits inherent complex concept abstractions in natural language to generalize concept-bottleneck methods to complex tasks.
arXiv Detail & Related papers (2022-06-21T06:22:35Z) - Visual Concepts Tokenization [65.61987357146997]
We propose an unsupervised transformer-based Visual Concepts Tokenization framework, dubbed VCT, to perceive an image into a set of disentangled visual concept tokens.
To obtain these concept tokens, we only use cross-attention to extract visual information from the image tokens layer by layer without self-attention between concept tokens.
We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.
arXiv Detail & Related papers (2022-05-20T11:25:31Z) - Corpus-level and Concept-based Explanations for Interpretable Document
Classification [23.194220621342254]
We propose a corpus-level explanation approach to capture causal relationships between keywords and model predictions.
We also propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction tasks.
arXiv Detail & Related papers (2020-04-24T20:54:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.