Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description of an overarching goal or data theme, which we call a realm, humans can often guess what concepts are associated with it. We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time. We use the large language model to generate text descriptions of semantically related classes that might potentially appear in the data stream in future. These descriptions are then rendered using Stable Diffusion to generate new labelled image samples. The resulting synthetic dataset is employed for supervised pre-training, but is discarded prior to commencing continual learning, along with the pre-training classification head. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem, thus becoming a valuable input to any existing continual learning method. Although there are complexities arising from the domain gap between real and synthetic images, we show that pre-training models in this manner improves multiple Class Incremenal Learning (CIL) methods on fine-grained image classification benchmarks.

There Will Be Blood begins nearly in silence. Its stunning opening 20 minutes follow a solitary figure as he struggles through an American wasteland, digging, bleeding, building. In its howling quiet, its violent yet graceful choreography, the film presents an iconic image of the ravages of greed, the inextricable link between the mythology of American exceptionalism and the circuits of capital--a lone tragic hero representing the creation of the American dream as well as its inevitable apocalyptic end. Paul Thomas Anderson's 2007 epic begins with one of cinema's greatest depictions of the desire and despair at the heart of American capitalism. But then, so does WALL-E. Nearly everything about the knockout opening of Anderson's masterpiece is also true of Pixar's masterpiece, released in theaters the following year, and, as of this week, the first film from the animation studio to be inducted into the vaunted Criterion Collection.

Early in his career, Andrew Hall, an old-school Miami attorney whose Coconut Grove firm has sued governments from Cuba to Sudan, worked on a lawsuit that lasted three full years. The case was cartoonishly complex. The Vietnam War was sputtering to an end and McDonnell Douglas Aircraft, then America's largest manufacturer of jet airplanes, had defaulted on a contract involving the delivery of 99 jets to Eastern Airlines. There were over a million documents put into evidence and almost 300 witnesses. The massive operation employed so many lawyers, clerks and paralegals, they resembled a legal militia more than a legal team.

Sophia, the worlds most advanced humanoid released to date was granted an honorary citizenship a few months ago by Saudi Arabia. In a move that set the net flooding with awe and dismay, this act probably triggered the first step towards recognising artificial intelligence being in the room and not at door step. The UN joined to recognise Sophia as the world's first UN Innovation Champion by UNDP. While these moves were music to many, artificial intelligence is raising a lot of divided opinions across the best of brains in science and technology. A quote widely in circulation on the social media on Einstein's premonition of a world having a generation of idiots may have its fair share of laughs. Einstein had indeed written a letter to his friend, psychiatrist Otto Juliusburger, in 1948 where he believed that the abominable deterioration of ethical standards stemmed primarily from the mechanisation and depersonalisation of our lives, a disastrous byproduct of science and technology.

It was an accidental discovery. Miami based start up, Premonition, was set up to do legal analytics. They assembled the World's largest litigation database and trained an artificial intelligence system to read it. While primarily focused on finding the performance of individual lawyers before specific judges to determine potential relationships, they noticed that a particularly prolific foreclosure attorney produced an 83% win rate for one of his bank clients, while another was only winning 16% of their foreclosures, essentially the same case types. "We couldn't figure it out and had all kinds of foolish theories why," Premonition co-founder and inventor, Toby Unwin confides.

Artificial intelligence is a big deal. It will change our society, and the way we do things. Just maybe not immediately, and in law it might be even longer. The function of artificial intelligence is directly connected to the concept of big data. The superior functioning of artificial intelligence over current processes is based in part on the superior ability of computing large amounts of information, data sets that are so large and so complex that the traditional means of processing this information simply isn't adequate enough when compared to techniques like predictive analytics.