spacer
home > ebr > summer 2020 > beyond big data
PUBLICATIONS
European Biopharmaceutical Review

Beyond Big Data

We’ve all seen and experienced the benefits that Big Data have brought to machine learning. Computers have become good at tasks like understanding human language and interpreting images – self-driving cars are arguably one of the most impressive examples.

Big Data mean that you have millions, if not billions, of observations and for each observation you have a manageable amount of data. For instance, when data scientists analyse Twitter data they have hundreds of millions of tweets; however, each tweet is less than 280 characters. In a nutshell, Big Data are when you want to learn something simple and you have an abundance of examples.

Most machine learning techniques work more efficiently when Big Data are provided. The availability of Big Data can sometimes eclipse the algorithms used. You might know the Modified National Institute of Standards and Technology data – they’re a large number of images (around 50,000) of hand-written digits (zero to nine) and tons of machine learning tutorials use this data set. Even the most basic machine learning models can identify 97% of the digits correctly. With complicated deep nets, you get up to 99.7% accuracy – showing how the most sophisticated artificial intelligence (AI) algorithm provides a whopping 2.7% increase.

Read full article from PDF >>

Rate this article You must be a member of the site to make a vote.  
Average rating:
0
     

There are no comments in regards to this article.

 You must be a member of the site to make a comment.
spacer
Joern Klinger is a developmental psychologist, computational linguist, geneticist, and entrepreneur. During his graduate studies in Oxford and Texas, Joern investigated human cognition in order to optimise AI. Insights from hands-on research in an indigenous community, neural-networks, and agent models led to an outside-the-box machine learning understanding, which he’s applying at his start-up biotx.ai.
spacer
Joern Klinger
spacer
spacer
Print this page
Send to a friend
Privacy statement
News and Press Releases

Creating your Secondary Packaging Strategy

Pharmaceutical and biotechnology companies with a drug product in clinical development are usually focused on a quick commercial launch. Secondary packaging aspects are often less considered. Correlations with secondary packaging (in this context, secondary packaging also includes device assembly and serialization) that are not considered in this phase can have a negative effect on: · further processability · options in the product lifecycle management · cost and time-to-market
More info >>

White Papers

Sourcing Commercial Drugs for Clinical Trials: US vs. EU Understanding the Differences

Myoderm

Sourcing commercial drugs for clinical trials is a dynamic process. There are many factors to consider: single source or regional sourcing, strategy, price, supply availability, lead times, and documentation are just a few. In the past, there were fewer clinical trials that required commercial drug sourcing, so demand was not as high. Today, the demand for commercial drugs in clinical trials has greatly increased and, as a result, inventory is tighter, orders are monitored more closely by manufacturers, and lead times have increased. This report highlights the key differences in sourcing from the US and EU.
More info >>

 
Industry Events

World Vaccine Congress Europe

18-21 October 2020, Barcelona, Spain

The World Vaccine Congress is an award-winning series of conferences and exhibitions that have grown to become the largest and most established vaccine meeting of its kind across the globe. Our credibility is show through the prestigious scientific advisory board that spend months of hard work creating a new and topical agenda, year on year.
More info >>

 

 

©2000-2011 Samedan Ltd.
Add to favourites

Print this page

Send to a friend
Privacy statement