paper-with-me

홈 › Papers

A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models

2018-10-09 · Ying Nian Wu, Ruiqi Gao, Tian Han, Song-Chun Zhu

The pattern theory of Grenander is a mathematical framework where patterns are represented by probability models on random variables of algebraic structures. In this paper, we review three families of probability models, namely, the discriminative models, the descriptive models, and the generative models. A discriminative model is in the form of a classifier. It specifies the conditional probability of the class label given the input signal. A descriptive model specifies the probability distribution of the signal, based on an energy function defined on the signal. A generative model assumes that the signal is generated by some latent variables via a transformation. We shall review these models within a common framework and explore their connections. We shall also review the recent developments that take advantage of the high approximation capacities of deep neural networks.

📄 PDF Abstract BibTeX arXiv:1810.04261

Code (0)

등록된 구현이 없습니다.

Tasks

Descriptive

Similar Papers 제목 키워드 기반

Semantic Integration in the Information Flow Framework

2018-10-18 · Robert E. Kent

The Information Flow Framework (IFF) is a descriptive category metatheory currently under development, which is being offered as the structural aspect of the Standard Upper Ontology (SUO). The architecture of the IFF is …

Descriptive

Beyond Co-occurrence: Multi-modal Session-based Recommendation

2023-09-29 · Xiaokun Zhang, Bo Xu, Fenglong Ma, Chenliang Li 외

Session-based recommendation is devoted to characterizing preferences of anonymous users based on short sessions. Existing methods mostly focus on mining limited item co-occurrence patterns exposed by item ID within sess…

Contrastive LearningDescriptiveRepresentation LearningSession-Based Recommendations

TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination

2025-10-26 · Omar Naim, Krish Sharma, Niyar R Barman, Nicholas Asher arxiv

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an infere…

Less Descriptive yet Discriminative: Quantifying the Properties of Multimodal Referring Utterances via CLIP

2022-05-01 · CMCL (ACL) 2022 5 · Ece Takmaz, Sandro Pezzelle, Raquel Fernández

In this work, we use a transformer-based pre-trained multimodal model, CLIP, to shed light on the mechanisms employed by human speakers when referring to visual entities. In particular, we use CLIP to quantify the degree…

Descriptive

Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families

2025-09-04 · Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla arxiv

Representational similarity metrics are fundamental tools in neuroscience and AI, yet we lack systematic comparisons of their discriminative power across model families. We introduce a quantitative framework to evaluate …