Artificial intelligence (AI), the simulation of human intelligence in machines, is changing the face of the legal industry. Law firms globally are apprehensive about what lies ahead for the industry but changes are already in motion and there is no escape, says Dr Anton Ravindran. Anton is the CEO of SmartLaw, a start-up based in Singapore that utilises AI to assist lawyers in their work. Its online services help lawyers scan through thousands of pages of documents and answer their law-related questions in seconds. It also helps them predict sentencing outcomes, and extract legal precedents and verdicts almost instantly for criminal offence, contested divorce and medical negligence.

To make good policy you should have at least a vague notion of what you're talking about. But when it comes to perhaps the biggest reform proposal around, we just don't. I'm talking about a Universal Basic Income, a system of unconditional cash payments to everybody in a given jurisdiction. The case for a UBI runs as follows: It would reduce poverty, make people healthier and give them more dignity. It would also ease the transition of workers who lose their jobs to robots or artificial intelligence, so they can retrain for different careers. In general, it lets people bridge periods out of work or in bad jobs so they can invest in their own skills and reenter the workforce at a higher level.

With increasingly widespread use of deep neural networks in critical decision-making applications, interpretability of these models is becoming imperative. We consider the problem of jointly learning a predictive model and its associated interpretation model. The task of the interpreter is to provide both local and global interpretability about the predictive model in terms of human-understandable high level attribute functions, without any loss of accuracy. This is achieved by a dedicated architecture and well chosen regularization penalties. We seek for a small-size dictionary of attribute functions that take as inputs the outputs of selected hidden layers and whose outputs feed a linear classifier. We impose a high level of conciseness by constraining the activation of a very few attributes for a given input with a real-entropy-based criterion while enforcing fidelity to both inputs and outputs of the predictive model. A major advantage of simultaneous learning is that the predictive neural network benefits from the interpretability constraint as well. We also develop a more detailed pipeline based on some common and novel simple tools to develop understanding about the learnt features. We show on two datasets, MNIST and QuickDraw, their relevance for both global and local interpretability.

Since modernity, ethic has been progressively fragmented into specific communities of practice. The digital revolution enabled by AI and Data is bringing ethical wicked problems in the crossroads of technology and behavior. However, the need of a comprehensive and constructive ethical framework is emerging as digital platforms connect us globally. The unequal structure of the global system makes that dynamic changes and systemic problems impact more on those that are most vulnerable. Ethical frameworks based only on the individual-level are not longer sufficient. A new ethical vision must comprise the understanding of the scales and complex interconnections of social systems. Many of these systems are internally fragile and very sensitive to external factors and threats, which turns into unethical situations that require systemic solutions. The high scale nature of digital technology that expands globally has also an impact at the individual level having the risk to make humans beings more homogeneous, predictable and ultimately controllable. To preserve the core of humanity ethic must take a stand to preserve and keep promoting individual rights and uniqueness and cultural heterogeneity tackling the negative trends and impact of digitalization. Only combining human-centered and collectiveness-oriented digital development it will be possible to construct new social models and human-machine interactions that are ethical. This vision requires science to enhance ethical frameworks and principles with the actionable insights of relationships and properties of the social systems that may not be evident and need to be quantified and understood to be solved. Artificial Intelligence is both a risk and and opportunity for an ethical development, thus we need a conceptual construct that drives towards a better digitalizated world.

When you harness the power and potential of machine learning, there are also some drastic downsides that you've got to manage. Deploying machine learning, you face the risk that it be discriminatory, biased, inequitable, exploitative, or opaque. In this article, I cover six ways that machine learning threatens social justice and reach an incisive conclusion: The remedy is to take on machine learning standardization as a form of social activism.When you harness the power and potential of machine learning, there are also some drastic downsides that you've got to manage. Deploying machine learning, you face the risk that it be discriminatory, biased, inequitable, exploitative, or opaque. In this article, I cover six ways that machine learning threatens social justice and reach an incisive conclusion: The remedy is to take on machine learning standardization as a form of social activism.When you use machine learning, you aren't just optimizing models and streamlining business.

While AI is poised to disrupt our work and lives, these technologies can be harnessed through wise regulation. So rather than replacing individuals, much AI should assist them in completing tasks that are more fulfilling, or by augmenting work that is often classified as professional. "Artificial intelligence (AI) has a proper substitutive role – it can ensure that difficult, dirty and dangerous work is done more and more by machines and less and less by human beings," says Professor Frank Pasquale from Brooklyn Law School."But Should people be taking more courses like computer science or technical fields that will help them understand AI better? "Yes, but I don't think they should replace existing courses.

Artificial intelligence, or AI, has long been the object of excitement and fear. In July, the Financial Times Future Forum think-tank convened a panel of experts to discuss the realities of AI -- what it can and cannot do, and what it may mean for the future. Entitled "The Impact of Artificial Intelligence on Business and Society", the event, hosted by John Thornhill, the innovation editor of the FT, featured Kriti Sharma, founder of AI for Good UK, Michael Wooldridge, professor of computer sciences at Oxford university, and Vivienne Ming, co-founder of Socos Labs. For the purposes of the discussion, AI was defined as "any machine that does things a brain can do". Intelligent machines under that definition still have many limitations: we are a long way from the sophisticated cyborgs depicted in the Terminator films. Such machines are not yet self-aware and they cannot understand context, especially in language. Operationally, too, they are limited by the historical data from which they learn, and restricted to functioning within set parameters. Rose Luckin, professor at University College London Knowledge Lab and author of Machine Learning and Human Intelligence, points out that AlphaGo, the computer that beat a professional (human) player of Go, the board game, cannot diagnose cancer or drive a car.

We present our HABERTOR model for detecting hatespeech in large scale user-generated content. Inspired by the recent success of the BERT model, we propose several modifications to BERT to enhance the performance on the downstream hatespeech classification task. HABERTOR inherits BERT's architecture, but is different in four aspects: (i) it generates its own vocabularies and is pre-trained from the scratch using the largest scale hatespeech dataset; (ii) it consists of Quaternion-based factorized components, resulting in a much smaller number of parameters, faster training and inferencing, as well as less memory usage; (iii) it uses our proposed multi-source ensemble heads with a pooling layer for separate input sources, to further enhance its effectiveness; and (iv) it uses a regularized adversarial training with our proposed fine-grained and adaptive noise magnitude to enhance its robustness. Through experiments on the large-scale real-world hatespeech dataset with 1.4M annotated comments, we show that HABERTOR works better than 15 state-of-the-art hatespeech detection methods, including fine-tuning Language Models. In particular, comparing with BERT, our HABERTOR is 4~5 times faster in the training/inferencing phase, uses less than 1/3 of the memory, and has better performance, even though we pre-train it by using less than 1% of the number of words. Our generalizability analysis shows that HABERTOR transfers well to other unseen hatespeech datasets and is a more efficient and effective alternative to BERT for the hatespeech classification.

Companies are leveraging data and artificial intelligence to create scalable solutions -- but they're also scaling their reputational, regulatory, and legal risks. For instance, Los Angeles is suing IBM for allegedly misappropriating data it collected with its ubiquitous weather app. Optum is being investigated by regulators for creating an algorithm that allegedly recommended that doctors and nurses pay more attention to white patients than to sicker black patients. Goldman Sachs is being investigated by regulators for using an AI algorithm that allegedly discriminated against women by granting larger credit limits to men than women on their Apple cards. Facebook infamously granted Cambridge Analytica, a political firm, access to the personal data of more than 50 million users.

Artificial intelligence, or AI, has long been the object of excitement and fear. In July, the Financial Times Future Forum think-tank convened a panel of experts to discuss the realities of AI -- what it can and cannot do, and what it may mean for the future. Entitled "The Impact of Artificial Intelligence on Business and Society", the event, hosted by John Thornhill, the innovation editor of the FT, featured Kriti Sharma, founder of AI for Good UK, Michael Wooldridge, professor of computer sciences at Oxford university, and Vivienne Ming, co-founder of Socos Labs. For the purposes of the discussion, AI was defined as "any machine that does things a brain can do". Intelligent machines under that definition still have many limitations: we are a long way from the sophisticated cyborgs depicted in the Terminator films. Such machines are not yet self-aware and they cannot understand context, especially in language. Operationally, too, they are limited by the historical data from which they learn, and restricted to functioning within set parameters. Rose Luckin, professor at University College London Knowledge Lab and author of Machine Learning and Human Intelligence, points out that AlphaGo, the computer that beat a professional (human) player of Go, the board game, cannot diagnose cancer or drive a car.