Learning feed-forward one-shot learners
نویسندگان
چکیده
One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they need large amounts of training data. In this paper, we propose a method to learn the parameters of a deep model in one shot. We construct the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar. In this manner we obtain an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one-shot classification objective in a learning to learn formulation. In order to make the construction feasible, we propose a number of factorizations of the parameters of the pupil network. We demonstrate encouraging results by learning characters from single exemplars in Omniglot, and by tracking visual objects from a single initial exemplar in the Visual Object Tracking benchmark.
منابع مشابه
Replacing Limit Learners with Equally Powerful One-Shot Query Learners
Different formal learning models address different aspects of human learning. Below we compare Gold-style learning—interpreting learning as a limiting process in which the learner may change its mind arbitrarily often before converging to a correct hypothesis—to learning via queries—interpreting learning as a one-shot process in which the learner is required to identify the target concept with ...
متن کاملFew-Shot Learning with Meta Metric Learners
Existing few-shot learning approaches are based on either meta-learning or metriclearning, which would suffer if the tasks have varying numbers of classes and/or the tasks diverge significantly. We propose meta metric learning to deal with the limitations of the existing few-shot learning approaches. Our meta metric learning approach consists of two components, task-specific learners that explo...
متن کاملEvolutionary Path to Biological Kernel Machines
A neural implementation of a support vector machine is described and applied to one-shot trainable pattern recognition. The model is compared to anatomical and dynamical properties of the olfactory system. In the olfactory model, inputs from the olfactory bulb are captured and stabilized in the anterior olfactory cortex and the kernel is computed in the posterior piriform cortex. The anterior p...
متن کاملTrain Once, Test Anywhere: Zero-Shot Learning for Text Classification
Zero-shot Learners are models capable of predicting unseen classes. In this work, we propose a Zero-shot Learning approach for text categorization. Our method involves training model on a large corpus of sentences to learn the relationship between a sentence and embedding of sentence’s tags. Learning such relationship makes the model generalize to unseen sentences, tags, and even new datasets p...
متن کاملComparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space
Different formal learning models address different aspects of learning. Below we compare learning via queries—interpreting learning as a one-shot process in which the learner is required to identify the target concept with just one hypothesis—to Gold-style learning—interpreting learning as a limiting process in which the learner may change its mind arbitrarily often before converging to a corre...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016