The latest issue of iA: Intelligent Architecture by Scott Brownrigg’s Design Research Unit focuses on the theme of ‘Architecture and Learning’. The edition explores not only the role of architecture on the design of educational buildings, but also the relationship between design, learning and the wider communities using Scott Brownrigg examples.

The article below 'Design Process: The Future in a word is Automation' is taken from Issue 7 and written by Scott Brownrigg Director Iain Macdonald. 

If Sage Wohns, Chief Executive of Agolo1 is correct in succinctly summarising the challenge facing business and education, educationalists and architects will have to consider the transformative impact of artificial intelligence (AI) and machine learning on teaching, pedagogy, facility design, programming, demographics, learning environments and tools. It is estimated EdTEch will be worth $120 Bn in the USA by 20192 in a country where already the ratio of computers per school student has changed from 1:125 in 1984 to 1:5 in 2012. Iain Macdonald explores how this is having a profound effect on how and where knowledge is transferred, practiced and assessed, and how as a consequence this is effecting internal and external configuration and aesthetics of educational facilities.

The boundaries are blurring or perhaps more accurately, blending formal and informal space as technology enables user groups to form and reform in a variety of ways to undertake different modules or extra-curricular activities. Moreover data analytics are increasingly being mined to guide programming of space both horizontally and vertically as well as influence solutions to locational and business demands for cost effective yet sustainable architecture which enhances student experience. The proliferation of personal and desktop technology is changing capital (capex) and operational (opex) expenditure on buildings. For example to suit LED and other visual displays, more sophisticated day and artificial lighting is required compared to the uniform lux associated with black and whiteboards of the last century. Increased use of technology requires resilient and expandable storage whether on or offsite, ,plus robust fibre connection and uninterrupted power supply all available for a price. The upside for education is borne out of recent research which indicates sampled student results have in general changed since EdTech has become more interactive and responsive, adopting the attributes of a teacher. Additionally technology is altering the way students and staff use their time, encouraging a shift away from the ‘factory’ model of education wherein students of a similar age are taught by the same teacher in the same way. This is due to AI enabling machines to learn about individual students by analysing data from their ICT usage, drawing upon insight into the science of learning is provided by ongoing cognitive and psychological research. Programmes are being developed using machine learning to find pupil specific error and strength patterns, such as China’s 17zuoye ‘ homework together’, which is used for students studying the English language.

What is ground breaking is that machine learning now enables computers to identify patterns not necessarily programmed, for example software Mindspark3 can recommend remedial training to avoid errors in value recognition known as ‘whole number thinking’ In the immediate future speech recognition and generation will further advance human/machine interface. The use of voice recognition to create virtual peers, enhanced by the introduction of features such as ‘vernacular’ or dialect will make students feel more comfortable using these interfaces, reinforcing cultural and demographic association. Whether promoting diversity by moving away from a common language will generate or reinforce a silo mentality is not yet apparent. Similarly while machine learning may pair excerpts from essays using comparative algorithms thus saving time to mitigate against teacher fatigue when marking, will it be able to comprehend the eclectic way in which humans at times construct arguments or arrive at a decision? Will it be able to improve the critique set out in an essay which may include attributes such irony, humour, nuance? What is evident is that learning environments will continue to host a range of physical as well as virtual spaces for a variety of tasks and use of different tools. California’s Alt Schools students consult their laptops for ‘portrait’ (personal progress information) and ‘playlist’ (material and work).

At AltSchools student screen time is limited to 35-40% of each school day. Freed from programming and various other preparation tasks, teachers are able to focus on analysing student ‘portrait’ data and deliver bespoke tutoring based on their individual needs. Some critics say school students should not dictate the pace of learning. Daniel Willingham of the University of Virginia states “If knowledge is cumulative it is important students acquire and retain facts necessary for developing critical thinking rather than default to a search engine.” Personalised learning, assessment and related results used by early adopters remains controversial for some stakeholders, and the same argument used against machine learning in the legal profession is also now being applied to the education sector. Similarly automated decision making (ADM) has generated consumer interest groups such as Algorithm Watch who argue society not just algorithm makers should determine the value judgements in ADMs’ true positives, false positives and positive predictive value (PPV)4 .

In business, cost remains paramount and education is not exempt. It is currently estimated that the cost per student at an EdTech school such as AltSchool is $27,000 per annum. Can high tech personalised learning work and be affordable in a state school system? Will partnering with technology and software companies provide a solution? Is there a pro bono alternative? How does education remain free of commercial influence? Can we avoid creating smart enclaves? Not all of these questions can be, or should be addressed by designers, but it is certain that there is a role for architects in imagining and realising future physical and virtual learning environments.

The publication reviews some of the current issues and trends affecting the design of future learning environments including the use and role of emerging technologies and artificial intelligence and the challenges associated with delivering learning environments on premium high density urban sites.  Click here to download iA Issue 7 or click below to view online.

The iA publication aims to cast a spotlight on those fields of research and design activities that can make a difference to the practice, the built environment and to a client’s projects, as well as on the individuals and groups that carried out that research.  Click here to view more of Scott Brownrigg's Publications and Research.