Search Results for author:
Found 15 papers, 7 papers with code
ANLS* -- A Universal Document Processing Metric for Generative Large Language Models
However, evaluating GLLMs presents a challenge as the binary true or false evaluation used for discriminative models is not applicable to the predictions made by GLLMs.
Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization
We show empirically that we can therefore train a "vanilla" fully connected network and convolutional neural network -- no skip connections, batch normalization, dropout, or any other architectural tweak -- with 500 layers by simply adding the batch-entropy regularization term to the loss function.
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing
Knowledge distillation maintains high performance and reaches high compression rates, nevertheless, the size of the student model is fixed after pre-training and can not be changed individually for a given downstream task and use-case to reach a desired performance/speedup ratio.
Auto-tuning of Deep Neural Networks by Conflicting Layer Removal
In the worst-case scenario, we prove that such a layer could lead to a network that cannot be trained at all.
Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks
Convolutional neural networks have established themselves over the past years as the state of the art method for image classification, and for many datasets, they even surpass humans in categorizing images.
Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks
In this paper, we introduce a novel theory and metric to identify layers that decrease the test accuracy of the trained models, this identification is done as early as at the beginning of training.
Evaluating the Progress of Deep Learning for Visual Relational Concepts
Convolutional Neural Networks (CNNs) have become the state of the art method for image classification in the last ten years.
Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification
Aspect-Target Sentiment Classification (ATSC) is a subtask of Aspect-Based Sentiment Analysis (ABSA), which has many applications e. g. in e-commerce, where data and insights from reviews can be leveraged to create value for businesses and customers.
Ranked #7 on
Aspect-Based Sentiment Analysis (ABSA)
on SemEval-2014 Task-4
(using extra training data)
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+5
Limitation of capsule networks
A recently proposed method in deep learning groups multiple neurons to capsules such that each capsule represents an object or part of an object.
Evaluating CNNs on the Gestalt Principle of Closure
Deep convolutional neural networks (CNNs) are widely known for their outstanding performance in classification and regression tasks over high-dimensional data.
Increasing the adversarial robustness and explainability of capsule networks with $γ$-capsules
In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior $\gamma$-capsule networks.
Guided Labeling using Convolutional Neural Networks
Over the last couple of years, deep learning and especially convolutional neural networks have become one of the work horses of computer vision.
Evaluation of Deep Learning on an Abstract Image Classification Dataset
Convolutional Neural Networks have become state of the art methods for image classification over the last couple of years.
25 years of CNNs: Can we compare to human abstraction capabilities?
We try to determine the progress made by convolutional neural networks over the past 25 years in classifying images into abstractc lasses.
Learning Abstract Classes using Deep Learning
Humans are generally good at learning abstract concepts about objects and scenes (e. g.\ spatial orientation, relative sizes, etc.).
