How the deep learning skills shortage is impacting businesses

Organisations at the forefront of AI are becoming increasingly aware of how the deep learning skills gap is becoming a pressing issue

Artificial intelligence innovator Peltarion has released a report showing that 83% of AI decision-makers believe that the skills shortage in deep learning is impacting their ability to compete at the top.

The report was produced from a survey of 350 CIOs or IT leaders from across the UK, Iceland, Sweden, Norway, Denmark, and Finland. Each of the surveyed decision-makers had direct responsibility for managing the direction of AI at companies with over 1,000 employees. 

Although 99% of decision-makers are planning to include research and development budgets for deep learning over the coming years, Peltarion’s research shows that many organisations are struggling to attract the right talent in order to support ambitious artificial intelligence projects.

Deep learning has a people problem

The research confirms that new approaches are needed, due to AI decision-makers relying heavily on hiring data science talent to plug the skills gap. At present, 71% of decision-makers are recruiting to address their skills shortage, but hiring from an outlying pool of talent is causing delays to projects, with almost half (49%) of respondents confirming that fact. 

44% of those surveyed believe that the need for more specialist skills, deep learning being perceived as the most conceptually complex, is ultimately blocking the path toward deep learning investment. The report shows that even though deep learning is growing in popularity, most IT specialists, data or computer scientists do not possess the skills required to lead a deep learning program. 

Deep learning risks of not investing

Today’s AI workforce is stretched thin

According to 49% of those surveyed, the skills shortage is delaying projects. Efforts are becoming more and more focused on constructing increasingly specialised teams of data scientists, and less about decentralising the workload. 93% of respondents said that their data scientists were becoming overworked and that inbound talent is more selective about which jobs to take on. 

The report states that “candidates who are on that market are in a position to be selective about where they take their skills and will often avoid companies without a mature deep learning program already in place.”

Businesses need deep learning preachers

The respondents agreed that deep learning programs require company-wide unification as they ultimately affect processes across the board. 96% said that businesses need an AI evangelist to instil the importance of such processes, and to educate employees, from engineers to managers, about in-house AI practices.

Deep learning issues to prevent investment

Key findings from the survey

  • 84% said their company leaders worry about the business risks associated with failing to invest in deep learning
  • 83% said that a shortfall of deep learning skills is impacting their ability to compete
  • 71% of AI decision-makers are actively recruiting to plug the skills gap
  • 49% said that the skills shortage is causing delays to projects
  • 44% believe the need for specialist skills is a roadblock to more investment in deep learning
  • 45% said they are finding it difficult to attract and hire talent because they lack a mature AI program
  • 93% said their data scientists are over-worked because there is no one to share the workload with

“This report shows that companies can’t afford to wait for data science talent to come to them to progress their AI projects.”

In a press-release, Co-founder and CEO of Peltarion Luka Crnkovic-Friis said: “This report shows that companies can’t afford to wait for data science talent to come to them to progress their AI projects. The fact is, many organisations are already starting to lose their competitive edge by waiting for specialised data scientists. The current approach, which relies on hiring an isolated team of data scientists to work on deep learning projects, is delaying projects and putting a strain on the talent companies do have.” 


READ MORE: Could deep learning come to an end?


Crnkovic-Friis said that in order to solve the deep learning skills gap, companies must utilise transferable talent which might already exist in-house. “Deep learning will only reach its true potential if we get more people from different areas of the business using it,” he said, “taking pressure off data scientists and allowing projects to progress.”

He concluded by saying that companies must make deep learning more affordable and accessible by reducing its complexity. “By operationalising deep learning to make it more scalable, affordable and understandable, organisations can put themselves on the fast track and use deep learning to optimise processes, create new products and add direct value to the business.” 

Luke Conrad

Technology & Marketing Enthusiast

The Future of Smart Buildings: Trends in Occupancy Monitoring

Khai Zin Thein • 12th June 2024

Occupancy monitoring technology is revolutionising building management with advancements in AI and IoT. AI algorithms analyse data from IoT sensors, enabling automated adjustments in lighting, HVAC, and security systems based on occupancy levels. Modern systems leverage big data and AI to optimise space usage and resource management, reducing energy consumption and promoting sustainability. Enhanced encryption...

The need to weave agility throughout the business

John Craig Swartz SVP at POWWR • 11th June 2024

With geopolitical tensions, more extreme weather events and the legacy of a global pandemic, it is more difficult for energy suppliers to preserve their margins and remain competitive than ever before. To thrive in the current climate, it is imperative that a supplier makes marginal gains wherever they can. Profitability within the sector today hinges...

Artificial general intelligence is closer than expected

AI expert Stuart Fenton • 10th June 2024

Whilst most of the attention around artificial intelligence (AI) thus far has been on ChatGPT, it is just the tip of the iceberg. In many ways, ChatGPT shouldn’t be thought of as true AI as it is – at its heart – just generative, learned behaviour. The future of AI, in contrast, is a system...

The State of Data Streaming

Confluent • 06th June 2024

Confluent survey: 90% of respondents say data streaming platforms can lead to more product and service innovation in AI and ML development 86% of respondents cite data streaming as a strategic or important priority for IT investments in 2024 For 91% of respondents, data streaming platforms are critical or important for achieving data-related goals

The State of Data Streaming

Confluent • 06th June 2024

Confluent survey: 90% of respondents say data streaming platforms can lead to more product and service innovation in AI and ML development 86% of respondents cite data streaming as a strategic or important priority for IT investments in 2024 For 91% of respondents, data streaming platforms are critical or important for achieving data-related goals

Grant Funding Awarded to Advance Cancer Therapeutics Discovery

Dr Alan Roth • 04th June 2024

The CRUK (Cancer Research UK) Scotland Institute and Oxford Drug Design, a biotechnology company with core expertise in AI drug discovery, have announced that their joint application for the MRC (UK Medical Research Council) National Mouse Genetics Network (NMGN) Business Engagement Fund has been awarded.