Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Will Deep Learning Make Other Machine Learning Algorithms Obsolete?

DZone's Guide to

Will Deep Learning Make Other Machine Learning Algorithms Obsolete?

The fourth (fifth?) quoranswer is here! This time we'll talk a bit about deep learning and its role in making other state of the art machine learning methods...

· AI Zone
Free Resource

Find out how AI-Fueled APIs from Neura can make interesting products more exciting and engaging. 

The next Quoranswer is here! This time, we'll talk a bit about deep learning and its role in making other state-of-the-art machine learning methods obsolete.

Will deep learning make other machine learning algorithms obsolete?

I will try to take a look at the question from the natural language processing perspective.

There is a class of problems in NLProc that might not be benefited from deep learning (DL) — at least directly. For the same reasons, machine learning (ML) cannot help so easily. I will give three examples, which share more or less the same property, so they're hard to model with ML or DL:

1. Sentiment Polarity

Here, I'm referring to identifying and analyzing a sentiment polarity oriented towards a particular object: person, brand, etc. Example: I like phone X, but dislike phone Y. If you monitor the sentiment situation for phone X, you'll expect this message to be positive, with negative polarity for phone Y. One can argue that it's doable and even easy to do with ML/DL, but I doubt you can stay solely within that framework. Most probably, you'll need a hybrid with a rule-based system, syntactic parsing, etc., which somewhat defeats the purpose of DL: be able to train neural network on a large amount of data without domain (linguist) knowledge.

2. Anaphora Resolution

There are systems that use ML (and hence, DL can be tried), like BART coreference system, but most of the research I have seen so far is based on some sort of rules/syntactic parsing (this presentation is quite useful). There is a vast application area for AR, including sentiment analysis and machine translation (also fact extraction, question-answering, etc). 

3. Machine Translation

Disambiguation, anaphora, object relations, syntax, semantics, and more in a single soup. Surely, you can try to model all of these with ML, but commercial systems in MT are more or less done with rules (plus machine learning recently). I'm expecting DL to produce advancements in MT. I'll cite one paper here that uses DL and improves on phrase-based SMT: [1409.3215] Sequence-to-Sequence Learning With Neural Networks.

Update: Here's a recent fun experiment with DL-based machine translation.

The list can be extended to knowledge bases etc, but I hope I made my point.

To find out how AI-Fueled APIs can increase engagement and retention, download Six Ways to Boost Engagement for Your IoT Device or App with AI today.

Topics:
ai ,deep learning ,machine learning ,algorithms ,machine translation ,nlp ,neural network

Published at DZone with permission of Dmitry Kan, DZone MVB. See the original article here.

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}