Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There is a growing need, however, for novel, brain-inspired cognitive architectures. The Global Workspace theory refers to a large-scale system integrating and distributing information among networks of specialized modules to create higher-level forms of cognition and awareness. We argue that the time is ripe to consider explicit implementations of this theory using deep learning techniques. We propose a roadmap based on unsupervised neural translation between multiple latent spaces (neural networks trained for distinct tasks, on distinct sensory inputs and/or modalities) to create a unique, amodal global latent workspace (GLW). Potential functional advantages of GLW are reviewed.

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, static word vectors continue to play an important role in tasks where word meaning needs to be modelled in the absence of linguistic context. In this paper, we explore how the contextualised embeddings predicted by BERT can be used to produce high-quality word vectors for such domains, in particular related to knowledge base completion, where our focus is on capturing the semantic properties of nouns. We find that a simple strategy of averaging the contextualised embeddings of masked word mentions leads to vectors that outperform the static word vectors learned by BERT, as well as those from standard word embedding models, in property induction tasks. We notice in particular that masking target words is critical to achieve this strong performance, as the resulting vectors focus less on idiosyncratic properties and more on general semantic properties. Inspired by this view, we propose a filtering strategy which is aimed at removing the most idiosyncratic mention vectors, allowing us to obtain further performance gains in property induction.

A growing attention in the empirical literature has been paid to the incidence of climate shocks and change in migration decisions. Previous literature leads to different results and uses a multitude of traditional empirical approaches. This paper proposes a tree-based Machine Learning (ML) approach to analyze the role of the weather shocks towards an individual's intention to migrate in the six agriculture-dependent-economy countries such as Burkina Faso, Ivory Coast, Mali, Mauritania, Niger, and Senegal. We perform several tree-based algorithms (e.g., XGB, Random Forest) using the train-validation-test workflow to build robust and noise-resistant approaches. Then we determine the important features showing in which direction they are influencing the migration intention. This ML-based estimation accounts for features such as weather shocks captured by the Standardized Precipitation-Evapotranspiration Index (SPEI) for different timescales and various socioeconomic features/covariates. We find that (i) weather features improve the prediction performance although socioeconomic characteristics have more influence on migration intentions, (ii) country-specific model is necessary, and (iii) international move is influenced more by the longer timescales of SPEIs while general move (which includes internal move) by that of shorter timescales.

Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches. Deep reinforcement learning has proven to be a powerful and effective framework for solving a diversity of challenging decision-making problems (Silver et al., 2017a; Berner et al., 2019). However these algorithms are typically trained to maximize a single reward function, ignoring information that is not directly relevant to the associated task at hand. This way of learning is in stark contrast to how humans learn (Tenenbaum, 2018). Without being prompted by a specific task, humans can still explore their environment, practice achieving imaginary goals, and in so doing learn about the dynamics of the environment. When subsequently presented with a novel task, humans can utilize this learned knowledge to bootstrap learning -- a property we would like our artificial agents to have. In this work, we investigate one way to bridge this gap by learning world models (Ha & Schmidhuber, 2018) that enable the realization of previously unseen tasks. By modeling the task-agnostic dynamics of an environment, an agent can make predictions about how its own actions may affect the environment state without the need for additional samples from the environment. Prior work has shown that by using powerful function approximators to model environment dynamics, training an agent entirely within its own world models can result in large gains in sample efficiency (Ha & Schmidhuber, 2018).

Mitigating the substantial undesirable impact of transportation systems on the environment is paramount. Thus, predicting Greenhouse Gas (GHG) emissions is one of the profound topics, especially with the emergence of intelligent transportation systems (ITS). We develop a deep learning framework to predict link-level GHG emission rate (ER) (in CO2eq gram/second) based on the most representative predictors, such as speed, density, and the GHG ER of previous time steps. In particular, various specifications of the long-short term memory (LSTM) networks with exogenous variables are examined and compared with clustering and the autoregressive integrated moving average (ARIMA) model with exogenous variables. The downtown Toronto road network is used as the case study and highly detailed data are synthesized using a calibrated traffic microsimulation and MOVES. It is found that LSTM specification with speed, density, GHG ER, and in-links speed from three previous minutes performs the best while adopting 2 hidden layers and when the hyper-parameters are systematically tuned. Adopting a 30 second updating interval improves slightly the correlation between true and predicted GHG ERs, but contributes negatively to the prediction accuracy as reflected on the increased root mean square error (RMSE) value. Efficiently predicting GHG emissions at a higher frequency with lower data requirements will pave the way to non-myopic eco-routing on large-scale road networks {to alleviate the adverse impact on the global warming

For Dr Mary-Anne Hartley, a medical doctor and researcher in EPFL's intelligent Global Health group (iGH), 2020 has been relentless. "It's not a relaxing time to study infectious diseases," she explained. Since the beginning of the COVID-19 pandemic, Dr Hartley's research team has been working non-stop with nearby Swiss university hospitals on two major projects. Using artificial intelligence (AI), they have developed new algorithms that, with data from ultrasound images and auscultation (chest/lung) sounds, can accurately diagnose the novel coronavirus in patients and predict how ill they are likely to become. "We've named the new deep learning algorithms DeepChest – using lung ultrasound images – and DeepBreath – using breath sounds from a digital stethoscope. This AI is helping us to better understand complex patterns in these fundamental clinical exams. So far, results are highly promising," said Professor Jaggi.

The evolution of human vision can be traced back to the very first primates that evolved 55 million years ago, a study of a tiny mammal from Madagascar found. The world's smallest primate, the endangered grey mouse lemur, is no bigger than an apple and weighs in at just two ounces. Researchers from Switzerland said that, despite their diminutive size, the endangered grey mouse lemur's visual system is just as big as that of other primates. In fact, more than a fifth of the big-eyed mammal's brain is dedicated to visual processing -- as compared to barely three percent of the human brain. The find highlights this brain region's incredible preservation and importance to our daily lives -- and those of our ancestors in the distant past.

For Dr. Mary-Anne Hartley, a medical doctor and researcher in EPFL's intelligent Global Health group (iGH), 2020 has been relentless. "It's not a relaxing time to study infectious diseases," she explained. Since the beginning of the COVID-19 pandemic, Dr. Hartley's research team has been working non-stop with nearby Swiss university hospitals on two major projects. Using artificial intelligence (AI), they have developed new algorithms that, with data from ultrasound images and auscultation (chest/lung) sounds, can accurately diagnose the novel coronavirus in patients and predict how ill they are likely to become. "We've named the new deep learning algorithms DeepChest--using lung ultrasound images--and DeepBreath--using breath sounds from a digital stethoscope. This AI is helping us to better understand complex patterns in these fundamental clinical exams. So far, results are highly promising," said Professor Jaggi.

Alphabet's Loon has been using algorithmic processes to optimize the flight of its stratospheric balloons for years now -- and setting records for time spent aloft as a result. But the company is now deploying a new navigation system that has the potential to be much better, and it's using true reinforcement-learning AI to teach itself to optimize navigation better than humans ever could. Loon developed the new reinforcement-learning system, which it says is the first to be used in an actual product aerospace context, with its Alphabet colleagues at Google AI in Montreal over the past couple of years. Unlike its past algorithmic navigation software, this one is devised entirely by machine -- a machine that's able to calculate the optimal navigation path for the balloons much more quickly than the human-made system could, and with much more efficiency, meaning the balloons use much less power to travel the same or greater distances than before. How does Loon know it's better?

Although Apple's latest A14 Bionic chip enabled the iPhone 12 family and iPad Air tablets to deliver impressive performance improvements, Qualcomm is making clear that the next generation of Android devices will rely heavily on advanced AI and computer vision processors to retake the performance lead. Teased yesterday at Qualcomm's virtual Tech Summit, the Snapdragon 888 is getting a full reveal today, and the year-over-year gains are impressive, notably including the largest jump in AI performance in Snapdragon history. The Snapdragon 888's debut is significant for technical decision makers because the chip will power most if not all of 2021's flagship Android phones, which collectively represent a large share of the over two billion computers sold globally each year. Moreover, the 888's increasing reliance on AI processing demonstrates how machine learning's role is now critical in advancing all areas of computing, ranging from how devices work when they're fully on to what they're quietly doing when not in active use. From a high-level perspective, the Snapdragon 888 is a sequel to last year's flagship 865 chips, leveraging 5-nanometer process technology and tighter integration with 5G and AI chips to deliver performance and power efficiency gains.