Biological organisms learn from interactions with their environment throughout their lifetime. For artificial systems to successfully act and adapt in the real world, it is desirable to similarly be able to learn on a continual basis. This challenge is known as lifelong learning, and remains to a large extent unsolved. In this perspective article, we identify a set of key capabilities that artificial systems will need to achieve lifelong learning. We describe a number of biological mechanisms, both neuronal and non-neuronal, that help explain how organisms solve these challenges, and present examples of biologically inspired models and biologically plausible mechanisms that have been applied to artificial intelligence systems in the quest towards development of lifelong learning machines. We discuss opportunities to further our understanding and advance the state of the art in lifelong learning, aiming to bridge the gap between natural and artificial intelligence.

No abstract

Historically, neuroscience principles have heavily influenced artificial intelligence (AI), for example the influence of the perceptron model, essentially a simple model of a biological neuron, on artificial neural networks. More recently, notable recent AI advances, for example the growing popularity of reinforcement learning, often appear more aligned with cognitive neuroscience or psychology, focusing on function at a relatively abstract level. At the same time, neuroscience stands poised to enter a new era of large-scale high-resolution data and appears more focused on underlying neural mechanisms or architectures that can, at times, seem rather removed from functional descriptions. While this might seem to foretell a new generation of AI approaches arising from a deeper exploration of neuroscience specifically for AI, the most direct path for achieving this is unclear. Here we discuss cultural differences between the two fields, including divergent priorities that should be considered when leveraging modern-day neuroscience for AI. For example, the two fields feed two very different applications that at times require potentially conflicting perspectives. We highlight small but significant cultural shifts that we feel would greatly facilitate increased synergy between the two fields.

No abstract

Sulfur colloid distribution on liver‐spleen scan is determined by the perfused Kupffer cell mass. The perfused Kupffer cell mass is proportional to the perfused hepatocyte mass, but is less affected by acute changes in hepatocyte function. Thus, sulfur colloid distribution parameters (precisely measured by quantitative liver‐spleen scan [QLSS]) may be an excellent test of the perfused hepatic mass. Although no gold standard exists for confirmation, a close correlation should exist between liver disease severity assessed at peritoneoscopy and sulfur colloid distribution. Peritoneoscopy severity (scored as total peritoneoscopy score [PS]; range, 0–5) was assessed in 76 patients who also had QLSS. Multivariate equation were generated to estimate liver disease severity from the QLSS. These were then applied prospectively in 20 consecutive patients to validate these equations. In 76 patients, 62 were evaluated because of chronic liver disease (CLD) and included those with micronodular (20) and macronodular (20) cirrhosis with various degrees of severity (Child's A, 16; B, 29; C, 17). Multivariate analysis yielded a number of combinations of QLSS parameters that correlated with peritoneoscopic severity. These equations were used to estimate liver disease severity. Estimates of liver disease severity (estimated PS [EPS]) correlated well with the PS in these 76 patients (r = .9064; r2 = .8216; P < .0001). Adding histological fibrosis to the QLSS parameters yields an equation for estimating PS that was even more effective (r = .9462; r2 = .8953; P < .001). However, validation of multivariate equations requires confirmation of their value in a second population. Applying these equations to a prospective group of 20 patients who subsequently had peritoneoscopic evaluation produced a similar correlation for QLSS parameters alone for estimating severity (r = .870; r2 = .757; P < .0001), and this was improved when the equation including histological fibrosis was added (r = .936; r2 = .877; P < .001). We believe these data support the QLSS as a quantitative estimate of the perfused hepatic mass that correlates with liver disease severity at peritoneoscopy. (HEPATOLOGY 1995; 22:1113–1121.).