In March of 2015, protests broke out at the University of Cape Town in South Africa over the campus statue of British colonialist Cecil Rhodes. Rhodes, a mining magnate who had gifted the land on which the university was built, had committed genocide against Africans and laid the foundations for apartheid. Under the rallying banner of "Rhodes Must Fall," students demanded that the statue be removed. Their protests sparked a global movement to eradicate the colonial legacies that endure in education. The events also provoked Shakir Mohamed, a South African AI researcher at DeepMind, to reflect on what colonial legacies might exist in his research as well.

Open-world learning is a problem where an autonomous agent detects things that it does not know and learns them over time from a non-stationary and never-ending stream of data; in an open-world environment, the training data and objective criteria are never available at once. The agent should grasp new knowledge from learning without forgetting acquired prior knowledge. Researchers proposed a few open-world learning agents for image classification tasks that operate in complex scenarios. However, all prior work on open-world learning has all labeled data to learn the new classes from the stream of images. In scenarios where autonomous agents should respond in near real-time or work in areas with limited communication infrastructure, human labeling of data is not possible. Therefore, supervised open-world learning agents are not scalable solutions for such applications. Herein, we propose a new framework that enables agents to learn new classes from a stream of unlabeled data in an unsupervised manner. Also, we study the robustness and learning speed of such agents with supervised and unsupervised feature representation. We also introduce a new metric for open-world learning without labels. We anticipate our theories and method to be a starting point for developing autonomous true open-world never-ending learning agents.

Peter Hotez deceives New York Times readers about the odds of dying from measles in the US to persuade parents to comply with the CDC's vaccine schedule. On January 9, the New York Times published an article written by Dr. Peter J. Hotez titled "You Are Unvaccinated and Got Sick. His purpose in writing is to persuade parents to vaccinate their children according to the routine schedule recommended by the Centers for Disease Control and Prevention (CDC). To that end, he purports to compare "the dangerous effects of three diseases with the minimal side effects of their corresponding vaccines." "To state it bluntly," Hotez writes, "being unvaccinated can result in illness or death. Vaccines, in contrast, are extremely unlikely to lead to side effects, even minor ones like fainting." He laments that "vaccination rates have fallen", resulting in a resurgence of measles globally. He cites the example of Samoa, where "almost 5,700 measles cases have been recorded since September, resulting in at least 83 deaths. Almost all of those who died were young children." In the US, he writes, "vaccine hesitancy is contributing to" measles outbreaks. Hotez presents data ostensibly to enable parents "to compare the risks of becoming ill with measles . . . to the minute chances of experiencing side effects from their corresponding vaccines." Hotez goes on to assert, "Moreover, new research reveals that, even when patients recover, the measles virus can suppress the immune system, rendering children susceptible to serious infections like pneumonia and the flu." "misinformation spread after an article implying a link between measles vaccinations and autism was published in The Lancet in 1998; it was retracted in 2010 over concerns about the validity of the results and the conduct of the study.

The Living Planet Index produced by WWF estimates that wildlife population sizes have dropped by 68 per cent since 1970. The charity advocates the use of artificial intelligence (AI) as a tool of conservation technology to monitor and curb this alarming rate of decline. One of the most useful applications is in acoustic monitoring, recording the sounds of wildlife ecosystems on weatherproof sensors. Many animals, from birds and bats to mammals and even invertebrates, use sound for communication, navigation and territorial defence, providing reams of rich data on how a species population is doing. AI provides a fast and cost-effective way to analyse hours of recordings for patterns of behaviour.

The Pentagon's Joint Artificial Intelligence Center has awarded a $93.3 million contract to General Atomics Aeronautical Systems Inc (GA-ASI), makers of the MQ-9 Reaper, to equip the drone with new AI technology. The aim is for the Reaper to be able to carry out autonomous flight, decide where to direct its battery of sensors, and to recognize objects on the ground. The contract, announced at the end of last month, builds on a successful test earlier this year. In some ways this is not a major development, more of an incremental step using existing technology. What makes it significant is the drone that is being equipped, and what it will be able to do afterwards.

The ubiquity of smart voice assistants has made conversational shopping commonplace. This is especially true for low consideration segments like grocery. A central problem in conversational grocery is the automatic generation of short product titles that can be read out fast during a conversation. Several supervised models have been proposed in the literature that leverage manually labeled datasets and additional product features to generate short titles automatically. However, obtaining large amounts of labeled data is expensive and most grocery item pages are not as feature-rich as other categories. To address this problem we propose a pre-training based solution that makes use of unlabeled data to learn contextual product representations which can then be fine-tuned to obtain better title compression even in a low resource setting. We use a self-attentive BiLSTM encoder network with a time distributed softmax layer for the title compression task. We overcome the vocabulary mismatch problem by using a hybrid embedding layer that combines pre-trained word embeddings with trainable character level convolutions. We pre-train this network as a discriminator on a replaced-token detection task over a large number of unlabeled grocery product titles. Finally, we fine tune this network, without any modifications, with a small labeled dataset for the title compression task. Experiments on Walmart's online grocery catalog show our model achieves performance comparable to state-of-the-art models like BERT and XLNet. When fine tuned on all of the available training data our model attains an F1 score of 0.8558 which lags the best performing model, BERT-Base, by 2.78% and XLNet by 0.28% only, while using 55 times lesser parameters than both. Further, when allowed to fine tune on 5% of the training data only, our model outperforms BERT-Base by 24.3% in F1 score.

Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues. On the one hand, the model updates sent by the clients at each training epoch might leak information on the clients' private data. On the other hand, the model learnt by the server may be subjected to attacks by malicious clients; these security attacks might poison the model or prevent it from converging. In this paper, we first examine security and privacy attacks to FL and critically survey solutions proposed in the literature to mitigate each attack. Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.

Are you prepared for AI implementation? Do you know what your accompanying data strategy should be? If not, it is likely you aren't alone. According to research by Secondmind, 82 per cent of supply chain managers are frustrated by AI systems and tools during the coronavirus pandemic. In its survey of 500-plus supply chain planners and managers across Europe and the United States, 37 per cent cited a lack of reliable data to feed into AI systems as a concern, at a time when accuracy and speed of decision-making were of the essence.

Around the world, artificial intelligence (AI) is automating functions and making new services possible with breakthroughs in low-cost computing power, cloud computing services, growth in big data and advancements in machine learning and related processes. This webinar discussed the current use of AI in low- and middle-income countries (LMICs), along with trends and challenges in business models, barriers to innovation and AI's ethical and responsible use towards achieving the sustainable development goals. This study examines the current use of AI in low- and middle-income countries (LMICs) across Sub-Saharan Africa, North Africa and South and Southeast Asia. The report mapped a sample of 450 start-ups by sector in alignment with the UN Sustainable ...

Generative adversarial network (GAN) is among the most popular deep learning models for learning complex data distributions. However, training a GAN is known to be a challenging task. This is often attributed to the lack of correlation between the training progress and the trajectory of the generator and discriminator losses and the need for the GAN's subjective evaluation. A recently proposed measure inspired by game theory - the duality gap, aims to bridge this gap. However, as we demonstrate, the duality gap's capability remains constrained due to limitations posed by its estimation process. This paper presents a theoretical understanding of this limitation and proposes a more dependable estimation process for the duality gap. At the crux of our approach is the idea that local perturbations can help agents in a zero-sum game escape non-Nash saddle points efficiently. Through exhaustive experimentation across GAN models and datasets, we establish the efficacy of our approach in capturing the GAN training progress with minimal increase to the computational complexity. Further, we show that our estimate, with its ability to identify model convergence/divergence, is a potential performance measure that can be used to tune the hyperparameters of a GAN.