Papers on Anderson de Andradehttps://deandrade.ca/papers/Recent content in Papers on Anderson de AndradeHugo -- 0.147.2enWed, 01 Apr 2026 00:00:00 +0000Rate-distortion optimization for transformer inferencehttps://deandrade.ca/papers/rd-transformers/Wed, 01 Apr 2026 00:00:00 +0000https://deandrade.ca/papers/rd-transformers/Split computing for language models, extending the theory of usable information.Lossy common information in a learnable Gray-Wyner Networkhttps://deandrade.ca/papers/common-information/Sun, 01 Feb 2026 00:00:00 +0000https://deandrade.ca/papers/common-information/Isolate the common information between two dependent computer vision tasks.Rate-distortion theory in coding for machines and its applicationshttps://deandrade.ca/papers/rd-cfm/Tue, 01 Jul 2025 00:00:00 +0000https://deandrade.ca/papers/rd-cfm/Theoretical considerations and evaluation of split and distillation points.Towards task-compatible compressible representationshttps://deandrade.ca/papers/towards-compatible/Thu, 01 Aug 2024 00:00:00 +0000https://deandrade.ca/papers/towards-compatible/Task reconstruction loss acts as a regularizer, increasing rate-distortion performance in coding for humans and machines.Base layer efficiency in scalable human-machine codinghttps://deandrade.ca/papers/base-efficiency/Sun, 01 Oct 2023 00:00:00 +0000https://deandrade.ca/papers/base-efficiency/Improving the shared channel in coding for machines (CfM).Conditional and residual methods in scalable coding for humans and machineshttps://deandrade.ca/papers/conditional-residual/Tue, 01 Aug 2023 00:00:00 +0000https://deandrade.ca/papers/conditional-residual/A comparison between conditional and residual entropy codecs for a two-channel systems of tasks with nested information.An architecture for accelerated large-scale inference of transformer-based language modelshttps://deandrade.ca/papers/transfomer-inference/Sun, 14 Feb 2021 00:00:00 +0000https://deandrade.ca/papers/transfomer-inference/Unified batch and online transformer inference.Graph representation learning network via adaptive samplinghttps://deandrade.ca/papers/gatas/Fri, 14 Feb 2020 00:00:00 +0000https://deandrade.ca/papers/gatas/Graph representations using a learnable attention mechanism to sample the neighbourhood of a graph.DENS: A dataset for multi-class emotion analysishttps://deandrade.ca/papers/dens/Fri, 01 Nov 2019 00:00:00 +0000https://deandrade.ca/papers/dens/Dataset for emotion classification of long-form narratives.Exploring multilingual syntactic sentence representationshttps://deandrade.ca/papers/syntatic-representations/Fri, 01 Nov 2019 00:00:00 +0000https://deandrade.ca/papers/syntatic-representations/Sentence embeddings augmented by universal parts-of-speech tags evaluated on low-resource languages.Unsupervised aspect extraction from free-form conversationshttps://deandrade.ca/papers/aspect-extraction/Tue, 01 Aug 2017 00:00:00 +0000https://deandrade.ca/papers/aspect-extraction/Dictionary-based approach for the extraction of "aspect-of" relationships.Best practices for convolutional neural networks applied to object recognition in imageshttps://deandrade.ca/papers/cnn-practices/Wed, 30 Apr 2014 00:00:00 +0000https://deandrade.ca/papers/cnn-practices/Evaluate the performance impact of optimization algorithms, activation functions, dropout, and maxout networks, in CNNs.A comparison of neural network training methods for text classificationhttps://deandrade.ca/papers/text-classification/Sun, 15 Dec 2013 00:00:00 +0000https://deandrade.ca/papers/text-classification/Benchmark of stochastic gradient descent and Nesterov's accelerated gradient for text classification.