Ladder Networks: Learning under Massive Label Deficit
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 7
Abstract
Advancement in deep unsupervised learning are finally bringing machine learning close to natural learning, which happens with as few as one labeled instance. Ladder Networks are the newest deep learning architecture that proposes semi-supervised learning at scale. This work discusses how the ladder network model successfully combines supervised and unsupervised learning taking it beyond the pre-training realm. The model learns from the structure, rather than the labels alone transforming it from a label learner to a structural observer. We extend the previously-reported results by lowering the number of labels, and report an error of 1.27 on 40 labels only, on the MNIST dataset that in a fully supervised setting, uses 60000 labeled training instances.
Authors and Affiliations
Behroz Mirza, Tahir Syed, Jamshed Memon, Yameen Malik
Keywords
Related Articles
- EP ID EP260686
- DOI 10.14569/IJACSA.2017.080769
- Views 75
- Downloads 0
Performance Measurement Model of Mobile User Connectivity in Femtocell/Macrocell Networks using Fractional Frequency Re-use Scheme
Technologies are traversing to its new dimensions every day. As part of this progression, mobile cellular system is at the summit of its constant advancement. The usage of Femtocells in mobile cellular system has created...
Development of knowledge Base Expert System for Natural treatment of Diabetes disease
The development of expert system for treatment of Diabetes disease by using natural methods is new information technology derived from Artificial Intelligent research using ESTA (Expert System Text Animation) Syste...
On Arabic Character Recognition Employing Hybrid Neural Network
Arabic characters illustrate intricate, multidimensional and cursive visual information. Developing a machine learning system for Arabic character recognition is an exciting research. This paper addresses a neural comput...
Designing and Building a Framework for DNA Sequence Alignment Using Grid Computing
Deoxyribonucleic acid (DNA) is a molecule that encodes unique genetic instructions used in the development and functioning of all known living organisms and many viruses. This Genetic information is encoded as a sequence...
An Effective Reasoning Algorithm for Question Answering System
Knowledge representation (KR) is the most desirable area of research to make the system intelligent. Today is the era of knowledge that requires articulations, semantic, syntax etc. These requirements, forced to de...