Training Decision Trees as Replacement for Convolution Layers
نویسندگان
چکیده
منابع مشابه
Finding Influential Training Samples for Gradient Boosted Decision Trees
We address the problem of finding influential training samples for a particular case of tree ensemble-based models, e.g., Random Forest (RF) or Gradient Boosted Decision Trees (GBDT). A natural way of formalizing this problem is studying how the model’s predictions change upon leave-one-out retraining, leaving out each individual training sample. Recent work has shown that, for parametric model...
متن کاملDecision trees as possibilistic classifiers
This paper addresses the classification problem with imperfect data. More precisely, it extends standard decision trees to handle uncertainty in both building and classification procedures. Uncertainty here is represented by means of possibility distributions. The first part investigates the issue of building decision trees from data with uncertain class values by developing a non-specificity b...
متن کاملCluster adaptive training with factorized decision trees for speech recognition
Cluster adaptive training (CAT) is a popular approach to train multiple-cluster HMMs for fast speaker adaptation in speech recognition. Traditionally, a cluster-independent decision tree is shared among all clusters, which could limit the modelling power of multiple-cluster HMMs. In this paper, each cluster is allowed to have its own decision tree. The intersections between the triphones subset...
متن کاملDecision Trees for Decision Making
If the company builds a big plant, it must live with it whatever the size of market demand. If it builds a small plant, management has the option of expanding the plant in two years in the event that demand is high during the introductory period; while in the event that demand is low during the introductory period, the company will maintain operations in the small plant and make a tidy profit o...
متن کاملA Kronecker-factored approximate Fisher matrix for convolution layers
Second-order optimization methods such as natural gradient descent have the potential to speed up training of neural networks by correcting for the curvature of the loss function. Unfortunately, the exact natural gradient is impractical to compute for large models, and most approximations either require an expensive iterative procedure or make crude approximations to the curvature. We present K...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i04.5801