We introduce a boosting framework to solve a classification problem with added manifold and ambient regularization costs. It allows for a natural extension of boosting into both semisupervised problems and unsupervised problems. The augmented cost is minimized in a greedy, stagewise functional minimization procedure as in GradientBoost. Our method provides insights into generalization issues in...

Strongly recurrent neural nets may show a continuously ongoing self-sustained activity, as it is the case for the brain. A new paradigm for learning is needed for neural nets being such autonomously active, since standard Hebbian-style online learning would result in uncontrolled reinforcement of accidental activity patterns. Here we propose that autonomously active neural networks processing a...

This paper describes a proof-of-the-principle experiment in which maximum entropy learning is used for the automatic induction of shallow morphological features for the resourcescarce Bantu language of Gı̃kũyũ. This novel approach circumvents the limitations of typical unsupervised morphological induction methods that employ minimum-edit distance metrics to establish morphological similarity bet...

This paper describes an application of active learning methods to the classification of phone strings recognized using unsupervised phonotactic models. The only training data required for classification using these recognition methods is assigning class labels to the audio files. The work described here demonstrates that substantial savings in this effort can be obtained by actively selecting e...

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce the manual annotation effort while achieving higher effectiveness compared to a set of baseline features. Unsupervised features are derived from skip-gram wor...

background:     purpose:     methods:     results:     conclusion:     key words:     pbl, lecture based method, education, frequent quizzes the variables such as changing the way of learning, using different methods in teaching, showing scientific films in class or, as a whole, active learning have significant effects on the results of final examination. the results showed that by changing the...

Supervised estimation methods are widely seen as being superior to semi and fully unsupervised methods. However, supervised methods crucially rely upon training sets that need to be manually annotated. This can be very expensive, especially when skilled annotators are required. Active learning (AL) promises to help reduce this annotation cost. Within the complex domain of HPSG parse selection, ...

We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our method for exploiting unsupervised learning of a probabilistic model can reduce the cost of building taggers with no dictionary and a small annotated corpus. Experimental results on English POS tagging and Japanese wo...