Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 7 of 7 for “"Length-Generalization"”.

  1. Beyond Memorization: Evaluating Length-Generalization in Transformer-based Language Models

    … However, transformers have trouble with length generalization (i.e., extrapolating on different lengths than seen during training). Recently, (Zhou et al., 2024a) proposed the RASP-Generalization Conjecture to predict what tasks are length-generalizable using a few carefully handcrafted …

    washington Repository record for Beyond Memorization: Evaluating Length-Generalization in Transformer-based Language Models (opens in a new tab)

  2. Exploring Patterns of Algorithmic Generalization in Deep Learning

    … deep learning systems ever exhibit algorithmic generalization? We investigate how deep learning systems can demonstrate algorithmic generalization, enabling them to handle problem instances of arbitrary size and complexity. We explore three patterns to achieve this goal: * Depth-wise recurrence: …

    toronto-retro Repository record for Exploring Patterns of Algorithmic Generalization in Deep Learning (opens in a new tab)

  3. Stimulus control of human punished behavior: Testing for generalization.

    … & Slivka, 1964) have investigated the stimulus generalization of punishment effects, or how they vary systematically with physical properties of stimuli. In a recent study with humans (O'Donnell & Crosbie, in press), each response in the presence of one horizontal line was punished, and …

    wvu Repository record for Stimulus control of human punished behavior: Testing for generalization. (opens in a new tab)

  4. On the Neural Architecture of Language Models

    … memory, with emphasis on out-of-distribution length generalization. Empirically, PR-LSTM generalizes to longer sequences on more tasks than standard RNN, LSTM, and Transformer baselines. These results show that recurrent computation can be reorganized hierarchically to improve parallel …

    ottawa-retro Repository record for On the Neural Architecture of Language Models (opens in a new tab)

  5. Unifying Neural and Symbolic Computation for Compositional Generalization: Representation and Processing

    … often fall short of the robust compositional generalization that characterizes human cognition, particularly in tasks demanding symbolic manipulation and algorithmic reasoning. This dissertation investigates the mechanisms underlying compositional generalization in neural networks and proposes …

    jhu Repository record for Unifying Neural and Symbolic Computation for Compositional Generalization: Representation and Processing (opens in a new tab)