When chief information officers think about their organizations and where machine learning might be deployed, the process often begins with an inventory of tasks. The CIOs and department leaders identify routine, repeatable processes that humans can pass off to computers. Then the operations and IT teams set up targeted programs to make those tasks more efficient. As legendary CIO Paul Strassmann has pointed out -- not without controversy -- it's a piecemeal approach that has become standard practice in most businesses. Strassmann's career includes serving as NASA's CIO from 2001 to 2003 and serving in an equivalent role in the Pentagon before that.

With more than 2000 spoken languages, Africa's linguistic diversity is second only to Asia. A third of the world's languages is spoken by the 1.2 billion people living within her 54 countries. But the language of artificial intelligence is yet to gain fluency. It has become hackneyed to weave AI into every conversation about technology and society. AI will take away jobs.

If recent television shows are anything to go by, we're a little concerned about the consequences of technological development. Black Mirror projects the negative consequences of social media, while artificial intelligence turns rogue in The 100 and Better Than Us. The potential extinction of the human race is up for grabs in Travellers, and Altered Carbon frets over the separation of human consciousness from the body. And Humans and Westworld see trouble ahead for human-android relations. Narratives like these have a long lineage.

Recurrent neural networks are extremely appealing for sequence-to-sequence learning tasks. Despite their great success, they typically suffer from a shortcoming: they are prone to generate unbalanced targets with good prefixes but bad suffixes, and thus performance suffers when dealing with long sequences. We propose a simple yet effective approach to overcome this shortcoming. Our approach relies on the agreement between a pair of target-directional RNNs, which generates more balanced targets. In addition, we develop two efficient approximate search methods for agreement that are empirically shown to be almost optimal in terms of either sequence level or non-sequence level metrics. Extensive experiments were performed on three standard sequence-to-sequence transduction tasks: machine transliteration, grapheme-to-phoneme transformation and machine translation. The results show that the proposed approach achieves consistent and substantial improvements, compared to many state-of-the-art systems.

The success and popularity of deep learning is on the rise, partially due to powerful deep learning frameworks such as TensorFlow and PyTorch that make it easier to develop deep learning models. However, these libraries also come with steep learning curves, since programming in these frameworks is quite different from traditional imperative programming with explicit loops and conditionals. In this work, we present a tool called TF-Coder for programming by example in TensorFlow. TF-Coder uses a bottom-up weighted enumerative search, with value-based pruning of equivalent expressions and flexible type- and value-based filtering to ensure that expressions adhere to various requirements imposed by the TensorFlow library. We also train models that predict TensorFlow operations from features of the input and output tensors and natural language descriptions of tasks, and use the models to prioritize relevant operations during the search. TF-Coder solves 63 of 70 real-world tasks within 5 minutes, often finding solutions that are simpler than those written by TensorFlow experts.

We present a solution to real-world train scheduling problems, involving routing, scheduling, and optimization, based on Answer Set Programming (ASP). To this end, we pursue a hybrid approach that extends ASP with difference constraints to account for a fine-grained timing. More precisely, we exemplarily show how the hybrid ASP system clingo[DL] can be used to tackle demanding planning-and-scheduling problems. In particular, we investigate how to boost performance by combining distinct ASP solving techniques, such as approximations and heuristics, with preprocessing and encoding techniques for tackling large-scale, real-world train scheduling instances.

Like'digital transformation', innovation is an over-used and under-examined term. This applies within business generally, but more especially within the public sector, where there are limits to the amount of disruption and risk that it is considered acceptable to carry within the public domain. Further, a range of questions arises when government'innovates'. These include building the culture and incentives for innovation; understanding what innovation in the digital era is actually about (clue: it's not simply about having a new idea); handling the public-private sector relationship differently; scaling innovations; and handling the politics that inevitably surround changes of almost any kind to public services. The opportunity to chair the second Public Sector Innovation Conference on 25 February was a great opportunity to reflect on these, and many of the other tensions and opportunities that surround ongoing modernisation of public services, and benefit from a really high-quality speaker lineup.

What are the different types of AI enabled offers formulated by AIBridge? AIBridge possesses industry agnostic products steered for equipping organizations for Digital Transformation and Process Automation, leveraging AI and ML capabilities. We have built an artificial intelligence enabled document extraction tool named AIMunshi. By leveraging AIMunshi invoice automation tool, users will be able to seamlessly process and transfer data across file systems and documents. This could further allow the workforce to concentrate on core processes and functions, accelerate processes, and enhance customer service.

Investment in artificial intelligence (AI) has been a priority for governments and businesses across the world. In Southeast Asia, the emphasis on AI-leadership is more pronounced with China's Premier incentivizing research efforts in the technology, and technology giants such as Alibaba and Tencent making massive strides in their quest for AI excellence. Research cited by Standards Australia, a standard setting non-profit, found that since 2017, 14 of the world's most advanced economies have announced over US$55 billion (AUD86 billion) in focused AI programs and activities. Australia, despite its government's efforts to help take the its agencies and businesses on a digital journey, hasn't made significant progress with AI. Standards Australia aims to change that.

So-called'soft skills' would seem to be the most important foundation to build upon. These include things like the ability to communicate and work well with others, solve problems, and think outside of the box. Most of the universities and private colleges in Australia are now offering short courses, online or on campus, to develop these critical skills. Courses include critical thinking and problem solving, negotiation and interpersonal skills, and effective communication. We can't predict what all the job roles will be in the 21st century, but we do know that human skills will be in demand.