2 results for “deep learning”

💻 Computer Science Master's

The Impact of Transformer Architectures on Machine Translation

Transformer architectures displaced recurrent models as the dominant paradigm in neural machine translation within three years of their introduction. This paper traces that displacement, arguing that the decisive advantage was not raw accuracy but parallelisability during training, which converted translation quality into a problem of available compute. It evaluates the empirical record across high- and low-resource language pairs and considers where the architecture's assumptions still break down.

724 words · 3 min read 🔒 1,200 tokens to unlock

🧠 Psychology Undergraduate

Cognitive Load Theory and the Design of Instructional Materials

Cognitive load theory holds that instructional design should minimise demands on working memory that do not contribute to learning. This essay examines the distinction between intrinsic, extraneous and germane load, reviews the worked-example and split-attention effects, and considers the expertise-reversal effect as a genuine constraint on the theory's prescriptions.

694 words · 3 min read 🔒 1,200 tokens to unlock