At Bleckwen we love reading books! For your summer break, we've compiled this list our favourite AI books. We are happy to share it with you. Cathy O'Neil (a Harvard PhD graduate in mathematics) has worked as a professor, hedge-fund analyst and data scientist. She founded ORCAA, an algorithmic auditing company.

Spending money on research and development is a funny thing. It's hard to tell what's going to be a success, and sometimes the results aren't valuable for decades. For example, Uber is investing heavily in driverless cars with the explicit goal of revolutionizing transportation. Even if the results aren't always successful we're convinced R&D investments are a leading indicator of long term economic strength. We found the numbers for our visualization thanks to the UNESCO Institute for Statistics, which collected the data through a series of smaller regional surveys.

Each week, we spotlight a cool innovation recommended by some of the industry's top tech writers. This week's pick is a new, intuitive way to pilot drones. Researchers at Switzerland's E cole Polytechnique Fe de rale de Lausanne have built a system that lets drone pilots steer their vehicles by just turning and twisting their torsos, said Megan Scudellari at IEEE Spectrum. The new technique turns out to be both more precise and more intuitive than using a joystick. In tests, researchers found that it "requires less mental focus from pilots and frees up their head and limbs."

Samsung is still two days away from officially unveiling its new Galaxy device, but a series of leaks surrounding the Note 9 in recent weeks means there's not much left to unveil. The 9 August "Unpacked" event has been preceded by numerous images and specs sheets revealing key features and details about the premium smartphone, including a possible price. Depending on the variant, the Galaxy Note 9 will cost between £899 (128GB version) and £1,099 (512GB version), according to the latest leak from Roland Quandt. So what can customers expect to get for this price? The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.

Affective computing [31] is "computing that relates to, arises from, or influences emotions." It is very important in human-machine interaction, as humans cannot have longlasting intimate relationships with machines if they cannot understand our affects and respond appropriately. Both affect classification and regression have been extensively studied in the literature [24], [43], [45], [46], [48]. For affect classification, the most commonly used categories are the six basic emotions (anger, disgust, fear, happiness, sadness, and surprise) proposed by Ekman et al. [5]. For regression, affects are usually represented as numbers in the 2D space of arousal and valence [35], or in the 3D space of arousal, valence, and dominance [25]. Recently, Yannakakis et al. [50] also argued that the nature of emotions is ordinal, and hence preference learning [51] should also play an important role in affective computing. Various input signals could be used in affective computing, e.g., speech [21], [47], facial expressions [8], [29], physiological signals [7], [43], and multimodal combination [26], [53]. Numerous features could be extracted from each modality. For example, 6,373 acoustic features were extracted by OpenSMILE [6] in the InterSpeech 2013 Computational Paralinguistics Challenge.

The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to discover new variations of the back-propagation equation. We use a domain specific lan- guage to describe update equations as a list of primitive functions. An evolution-based method is used to discover new propagation rules that maximize the generalization per- formance after a few epochs of training. We find several update equations that can train faster with short training times than standard back-propagation, and perform similar as standard back-propagation at convergence.

The multi-armed bandit is a sequential allocation task where an agent must learn a policy that maximizes long term payoff, where only the reward of the played arm is observed at each iteration. In the stochastic setting, the reward for each action is generated from an unknown distribution, which depends on a given 'context', available at each interaction with the world. Thompson sampling is a generative, interpretable multi-armed bandit algorithm that has been shown both to perform well in practice, and to enjoy optimality properties for certain reward functions. Nevertheless, Thompson sampling requires sampling from parameter posteriors and calculation of expected rewards, which are possible for a very limited choice of distributions. We here extend Thompson sampling to more complex scenarios by adopting a very flexible set of reward distributions: nonparametric Gaussian mixture models. The generative process of Bayesian nonparametric mixtures naturally aligns with the Bayesian modeling of multi-armed bandits. This allows for the implementation of an efficient and flexible Thompson sampling algorithm: the nonparametric model autonomously determines its complexity in an online fashion, as it observes new rewards for the played arms. We show how the proposed method sequentially learns the nonparametric mixture model that best approximates the true underlying reward distribution. Our contribution is valuable for practical scenarios, as it avoids stringent model specifications, and yet attains reduced regret.

This paper studies a class of adaptive gradient based momentum algorithms that update the search directions and learning rates simultaneously using past gradients. This class, which we refer to as the "Adam-type", includes the popular algorithms such as the Adam, AMSGrad and AdaGrad. Despite their popularity in training deep neural networks, the convergence of these algorithms for solving nonconvex problems remains an open question. This paper provides a set of mild sufficient conditions that guarantee the convergence for the Adam-type methods. We prove that under our derived conditions, these methods can achieve the convergence rate of order $O(\log{T}/\sqrt{T})$ for nonconvex stochastic optimization. We show the conditions are essential in the sense that violating them may make the algorithm diverge. Moreover, we propose and analyze a class of (deterministic) incremental adaptive gradient algorithms, which has the same $O(\log{T}/\sqrt{T})$ convergence rate. Our study could also be extended to a broader class of adaptive gradient methods in machine learning and optimization.

Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a large number of unlabeled samples, but time-consuming or expensive to label them. Active learning for regression (ALR) is a methodology to reduce the number of labeled samples, by selecting the most beneficial ones to label, instead of random selection. This paper proposes two new ALR approaches based on greedy sampling (GS). The first approach (GSy) selects new samples to increase the diversity in the output space, and the second (iGS) selects new samples to increase the diversity in both input and output spaces. Extensive experiments on 12 UCI and CMU StatLib datasets from various domains, and on 15 subjects on EEG-based driver drowsiness estimation, verified their effectiveness and robustness.

This paper presents a light-weight and accurate deep neural model for audiovisual emotion recognition. To design this model, the authors followed a philosophy of simplicity, drastically limiting the number of parameters to learn from the target datasets, always choosing the simplest earning methods: i) transfer learning and low-dimensional space embedding allows to reduce the dimensionality of the representations. ii) The isual temporal information is handled by a simple score-per-frame selection process, averaged across time. iii) A simple frame selection echanism is also proposed to weight the images of a sequence. iv) The fusion of the different modalities is performed at prediction level (late usion). We also highlight the inherent challenges of the AFEW dataset and the difficulty of model selection with as few as 383 validation equences. The proposed real-time emotion classifier achieved a state-of-the-art accuracy of 60.64 % on the test set of AFEW, and ranked 4th at he Emotion in the Wild 2018 challenge.