Word Embedding Captures Semantic Relationships
November 10, 2016
The article on O’Reilly titled Capturing Semantic Meanings Using Deep Learning explores word embedding in natural language processing. NLP systems typically encode word strings, but word embedding offers a more complex approach that emphasizes relationships and similarities between words by treating them as vectors. The article posits,
For example, let’s take the words woman, man, queen, and king. We can get their vector representations and use basic algebraic operations to find semantic similarities. Measuring similarity between vectors is possible using measures such as cosine similarity. So, when we subtract the vector of the word man from the vector of the word woman, then its cosine distance would be close to the distance between the word queen minus the word king (see Figure 1).
The article investigates the various neural network models that prevent the expense of working with large data. Word2Vec, CBOW, and continuous skip-gram are touted as models and the article goes into great technical detail about the entire process. The final result is that the vectors understand the semantic relationship between the words in the example. Why does this approach to NLP matter? A few applications include predicting future business applications, sentiment analysis, and semantic image searches.
Chelsea Kerwin, November 10, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
The Machine Learning Textbook
July 19, 2016
Deep learning is another bit of technical jargon floating around and it is tied to artificial intelligence. We know that artificial intelligence is the process of replicating human thought patterns and actions through computer software. Deep learning is…well, what specifically? To get a primer on what deep learning is as well as it’s many applications check out “Deep Learning: An MIT Press Book” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
Here is how the Deeping Learning book is described:
“The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free. The print version will be available for sale soon.”
This is a fantastic resource to take advantage of. MIT is one of the leading technical schools in the nation, if not the world, and the information that is sponsored by them is more than guaranteed to round out your deep learning foundation. Also it is free, which cannot be beaten. Here is how the book explains the goal of machine learning:
“This book is about a solution to these more intuitive problems. This solution is to allow computers to learn from experience and understand the world in terms of a hierarchy of concepts, with each concept de?ned in terms of its relation to simpler concepts. By gathering knowledge from experience, this approach avoids the need for human operators to formally specify all of the knowledge that the computer needs.”
If you have time take a detour and read the book, or if you want to save time there is always Wikipedia.
Whitney Grace, July 19, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
There is a Louisville, Kentucky Hidden Web/Dark
Web meet up on July 26, 2016.
Information is at this link: http://bit.ly/29tVKpx.
MIT Discover Object Recognition
June 23, 2015
MIT did not discover object recognition, but researchers did teach a deep-learning system designed to recognize and classify scenes can also be used to recognize individual objects. Kurzweil describes the exciting development in the article, “MIT Deep-Learning System Autonomously Learns To Identify Objects.” The MIT researchers realized that deep-learning could be used for object identification, when they were training a machine to identify scenes. They complied a library of seven million entries categorized by scenes, when they learned that object recognition and scene-recognition had the possibility of working in tandem.
“ ‘Deep learning works very well, but it’s very hard to understand why it works — what is the internal representation that the network is building,’ says Antonio Torralba, an associate professor of computer science and engineering at MIT and a senior author on the new paper.”
When the deep-learning network was processing scenes, it was fifty percent accurate compared to a human’s eighty percent accuracy. While the network was busy identifying scenes, at the same time it was learning how to recognize objects as well. The researchers are still trying to work out the kinks in the deep-learning process and have decided to start over. They are retraining their networks on the same data sets, but taking a new approach to see how scene and object recognition tie in together or if they go in different directions.
Deep-leaning networks have major ramifications, including the improvement for many industries. However, will deep-learning be applied to basic search? Image search still does not work well when you search by an actual image.
Whitney Grace, June 23, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
-
- Subscribe to Beyond Search
Feature archive
News archive
-
