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 84
- Downloads 0
Software Architecture- Evolution and Evaluation
The growth of various software architectural frameworks and models provides a standard governing structure for different types of organizations. Selection of a suitable framework for a particular environment needs much m...
A New Hybrid Network Sniffer Model Based on Pcap Language and Sockets (Pcapsocks)
Nowadays, the protection and the security of data transited within computer networks represent a real challenge for developers of computer applications and network administrators. The Intrusion Detection System and Intru...
A Robust Hash Function Using Cross-Coupled Chaotic Maps with Absolute-Valued Sinusoidal Nonlinearity
This paper presents a compact and effective chaos-based keyed hash function implemented by a cross-coupled topology of chaotic maps, which employs absolute-value of sinusoidal nonlinearity, and offers robust chaotic regi...
A Vertical Handover Management for Mobile Telemedicine System using Heterogeneous Wireless Networks
Application of existing mobile telemedicine system is restricted by the imperfection of network coverage, network capacity, and mobility. In this paper, a novel telemedicine based handover decision making (THODM) algorit...
Semantic Sentiment Analysis of Arabic Texts
Twitter considered as a rich resource to collect people's opinions in different domains and attracted researchers to develop an automatic Sentiment Analysis (SA) model for tweets. In this work, a semantic Arabic Twitter...