اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدOn the Dynamics of Training Attention Models
106
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The attention mechanism has been widely used in deep neural networks as a model component. By now, it has become a critical building block in many state-of-the-art natural language models. Despite its great success established empirically, the working mechanism of attention has not been investigated at a sufficient theoretical depth to date. In this paper, we set up a simple text classification task and study the dynamics of training a simple attention-based classification model using gradient descent. In this setting, we show that, for the discriminative words that the model should attend to, a persisting identity exists relating its embedding and the inner product of its key and the query. This allows us to prove that training must converge to attending to the discriminative words when the attention output is classified by a linear classifier. Experiments are performed, which validate our theoretical analysis and provide further insights.
قيم البحث
اقرأ أيضاً
We introduce talking-heads attention - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional par
ameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.
Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly plastic, lackin
g the stability necessary to prevent the forgetting of previous knowledge, which means that as learning progresses, networks tend to forget previously seen tasks. This phenomenon coined in the continual learning literature, has attracted much attention lately, and several families of approaches have been proposed with different degrees of success. However, there has been limited prior work extensively analyzing the impact that different training regimes -- learning rate, batch size, regularization method-- can have on forgetting. In this work, we depart from the typical approach of altering the learning algorithm to improve stability. Instead, we hypothesize that the geometrical properties of the local minima found for each task play an important role in the overall degree of forgetting. In particular, we study the effect of dropout, learning rate decay, and batch size, on forming training regimes that widen the tasks local minima and consequently, on helping it not to forget catastrophically. Our study provides practical insights to improve stability via simple yet effective techniques that outperform alternative baselines.
Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm. In this work w
e present emph{Population Based Training (PBT)}, a simple asynchronous optimisation algorithm which effectively utilises a fixed computational budget to jointly optimise a population of models and their hyperparameters to maximise performance. Importantly, PBT discovers a schedule of hyperparameter settings rather than following the generally sub-optimal strategy of trying to find a single fixed set to use for the whole course of training. With just a small modification to a typical distributed hyperparameter training framework, our method allows robust and reliable training of models. We demonstrate the effectiveness of PBT on deep reinforcement learning problems, showing faster wall-clock convergence and higher final performance of agents by optimising over a suite of hyperparameters. In addition, we show the same method can be applied to supervised learning for machine translation, where PBT is used to maximise the BLEU score directly, and also to training of Generative Adversarial Networks to maximise the Inception score of generated images. In all cases PBT results in the automatic discovery of hyperparameter schedules and model selection which results in stable training and better final performance.
Training a neural network model can be a lifelong learning process and is a computationally intensive one. A severe adverse effect that may occur in deep neural network models is that they can suffer from catastrophic forgetting during retraining on
new data. To avoid such disruptions in the continuous learning, one appealing property is the additive nature of ensemble models. In this paper, we propose two generic ensemble approaches, gradient boosting and meta-learning, to solve the catastrophic forgetting problem in tuning pre-trained neural network models.
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are design
ed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are trivial for powerful servers, but critical for edge devices. To mitigate these issues, We propose Resource Constrained Training (RCT). RCT only keeps a quantised model throughout the training, so that the memory requirements for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically in order to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image application and natural language processing. Experiments show that RCT saves more than 86% energy for General Matrix Multiply (GEMM) and saves more than 46% memory for model parameters, with limited accuracy loss. Comparing with QAT-based method, RCT saves about half of energy on moving model parameters.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
