Dive Brief:

• Deep learning will be a key driver of performance in demand, fraud and failure predictions by 2019, according to Gartner. The technology builds upon machine learning with the provision of intermediate data representations.

• Applications changing focus to predictive analysis from image, text and audio processing need business buy-in, infrastructure and talented data scientists. Approximately 80% of data scientists believe the variation of machine learning will be part of their tool kits by next year.

• Although deep learning and machine learning offer tremendous data processing capabilities, Gartner cautioned that the technologies are not a replacement for human workers. Data scientists are needed alongside deep learning applications to judge the ethics of recommended decisions. "What's hard for people is easy for ML, and what's hard for ML is easy for people," said Alexander Linden, research VP at Gartner, in a statement.

Dive Insight:

Early adopters of AI, machine learning and deep learning are expected to reap in creative and productive benefits in the short and long term. Major service providers have steadily upped their deep learning investments.

Intel acquired deep learning startup Nervana Systems at the end of last year to the tune of around $400 million. The acquisition was an integral part of the company's expanding AI portfolio, which grew this week with $1 billion in investments to AI startups.

NVIDIA expanded its Deep Learning Institute curriculum this spring to include deep learning applications in technologies like robotics, financial services, self-driving cars and healthcare. IBM's PowerAI DDL technique to reduce training time for distributed deep learning systems was announced in August. The program hit a 95% scaling efficiency, beating out Facebook's 89% prior record.

The demand for qualified human accompaniment to these deep learning systems may strain the IT talent shortage the industry already faces. Companies need to invest in a workforce capable of working side-by-side to deep learning and other AI applications.