DeepMind to Develop Neural Arithmetic Logic Units

According to researchers, new architecture allows neural networks to perform number-related tasks more efficiently
16 August 2018   2081

A team of researchers from DeepMind has developed a new architecture that allows neural networks to perform number-related tasks more efficiently. It involves the creation of a module with the basic mathematical operations described in it. The module was named Neural Arithmetic Logic Unit (NALU).

Scientists have noticed that neural networks are rarely able to successfully generalize concepts beyond the data set on which they were trained. For example, when working with numbers, models don't extrapolate the data to high-order quantities. After studying the problem, the researchers found that it also extends to other arithmetic functions.

When standard neural architectures are trained to count to a number, they often struggle to count to a higher one. We explored this limitation and found that it extends to other arithmetic functions as well, leading to our hypothesis that neural networks learn numbers similar to how they learn words, as a finite vocabulary. This prevents them from properly extrapolating functions requiring previously unseen (higher) numbers. Our objective was to propose a new architecture which could perform better extrapolation.
 

Andrew Trask

Lead researcher, NALU

The structure with NALU suggests predetermining a set of basic, potentially useful mathematical functions (addition, subtraction, division and multiplication). Subsequently, the neural network itself decides where these functions are best used, rather than figuring out from scratch what it is.

The tests showed that neural networks with a new architecture are capable of learning tasks such as tracking time periods, performing arithmetic operations on image numbers, counting objects on a picture, and executing computer code. 

In March 2018, DeepMind introduced a new paradigm for learning AI models. Unlike standard methods, it does not require a large set of input data: the algorithm learns to perform tasks independently, gradually mastering the necessary skills.

BNC to Monitor BTC Community's Mood

The system called Twitter Sentiment analyzes over 34M BTC-related Twitter posts each week, using AI to track the mood of the community
22 January 2020   471

Blockchain-based New Zealand-based research firm Brave New Coin (BNC) has unveiled a new system for measuring the mood of the Bitcoin community based on Twitter messages.

According to BNC, the new Twitter Sentiment rating system analyzes over 34 million BTC-related Twitter posts each week. The company uses artificial intelligence (AI) algorithms that look for records containing the words bitcoin, $ BTC and BTC and others.

BNC notes that user sentiment continues to be a “significant” factor in the price and dynamics of digital assets, and a new technique has been developed to track these sentiments. According to the BNC, it took 18 months to launch the Bitcoin Twitter Sentiment. The data obtained is divided into seven categories - Opinion, Technical Information, Inside the Network, Advertising, Bots, Macros and Hacking.

For the week ending January 17, the most common entries were in the Opinion category - their number was 30.42% of all data received. In second place was the category Technical Information, and in third inside the network (includes information on mining and hashrate).

BNC spokeswoman Pierre Ansaldi said that during the first quarter of this year, the company will also launch community sentiment analysis tools for other crypto assets.