Unsupervised Deep Learning Recommender System for Personal Computer Users

This work presents an unsupervised learning approach for training a virtual assistant recommender system, building upon prior work on deep learning neural networks, image processing, mixed-initiative systems, and recommender systems. Intelligent agents can understand the world in intuitive ways with neural networks, and make action recommendations to computer users. The system discussed in this work interprets a computer screen image in order to learn new keywords from the user’s screen and associate them to new contexts in a completely unsupervised way, then produce action recommendations to assist the user. It can assist in automating various tasks such as genetics research, computer programming, engaging with social media, and legal research. The action recommendations are personalized to the user, and are produced without integration of the assistant into each individual application executing on the computer. Recommendations can be accepted with a single mouse click by

[1]  Eduardo F. Morales,et al.  An Introduction to Reinforcement Learning , 2011 .

[2]  Ping Chen,et al.  Extended Topic Model for Word Dependency , 2015, ACL.

[3]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[4]  Luis Pedro Coelho,et al.  Building Machine Learning Systems with Python , 2013 .

[5]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[6]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Martin van den Berg,et al.  Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery , 1999, Comput. Networks.

[8]  Mark Levene,et al.  Mining named entities from search engine query logs , 2014, IDEAS.

[9]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[10]  Emilio Soria Olivas,et al.  Handbook of Research on Machine Learning Applications and Trends : Algorithms , Methods , and Techniques , 2009 .

[11]  Matthias Samwald,et al.  Applying deep learning techniques on medical corpora from the World Wide Web: a prototypical system and evaluation , 2015, ArXiv.

[12]  Yi Zhang,et al.  Using big data from the web to train Chinese traffic word representation model in vector space , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[13]  Doug Downey,et al.  Unsupervised named-entity extraction from the Web: An experimental study , 2005, Artif. Intell..

[14]  Grant Potter,et al.  TinEye Reverse Image Search , 2017 .

[15]  Dana H. Ballard,et al.  Modular Learning in Neural Networks , 1987, AAAI.

[16]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[17]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[18]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[19]  Eric Crestan,et al.  Web-Scale Distributional Similarity and Entity Set Expansion , 2009, EMNLP.

[20]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[21]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[22]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[23]  Abhinandan Das,et al.  Google news personalization: scalable online collaborative filtering , 2007, WWW '07.

[24]  Dong Yu,et al.  Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[27]  Jürgen Schmidhuber,et al.  Learning Complex, Extended Sequences Using the Principle of History Compression , 1992, Neural Computation.

[28]  Gregory Grefenstette,et al.  Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler , 2016, ArXiv.

[29]  Tom Gedeon,et al.  Use of Noise to Augment Training Data: A Neural Network Method of Mineral–Potential Mapping in Regions of Limited Known Deposit Examples , 2003 .

[30]  William W. Cohen,et al.  Automatic Set Expansion for List Question Answering , 2008, EMNLP.

[31]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[32]  Ralph Grishman,et al.  Towards Large-Scale Unsupervised Relation Extraction from the Web , 2012, Int. J. Semantic Web Inf. Syst..

[33]  William W. Cohen,et al.  Language-Independent Set Expansion of Named Entities Using the Web , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[34]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

[35]  Peter D. Turney.  Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL , 2001, ECML.

[36]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.