Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature. We use a first principles approach to explain LR and RP, and show a connection between the two via the divergence theorem. The theory motivated us to derive optimal importance sampling schemes to reduce LR gradient variance. Our newly derived distributions have analytic probability densities and can be directly sampled from. The improvement for Gaussian target distributions was modest, but for other distributions such as a Beta distribution, our method could lead to arbitrarily large improvements, and was crucial to obtain competitive performance in evolution strategies experiments.

Choosing the most adequate kernel is crucial in many Machine Learning applications. Gaussian Process is a state-of-the-art technique for regression and classification that heavily relies on a kernel function. However, in the Gaussian Process literature, kernels have usually been either ad hoc designed, selected from a predefined set, or searched for in a space of compositions of kernels which have been defined a priori. In this paper, we propose a Genetic-Programming algorithm that represents a kernel function as a tree of elementary mathematical expressions. By means of this representation, a wider set of kernels can be modeled, where potentially better solutions can be found, although new challenges also arise. The proposed algorithm is able to overcome these difficulties and find kernels that accurately model the characteristics of the data. This method has been tested in several real-world time-series extrapolation problems, improving the state-of-the-art results while reducing the complexity of the kernels.

Sensitive synthetic skin enables robots to sense their own bodies and surroundings--a crucial capability if they are to be in close contact with people. Inspired by human skin, a team at the Technical University of Munich (TUM) has developed a system combining artificial skin with control algorithms and used it to create the first autonomous humanoid robot with full-body artificial skin. The artificial skin developed by Prof. Gordon Cheng and his team consists of hexagonal cells about the size of a two-euro coin (i.e. about one inch in diameter). Each is equipped with a microprocessor and sensors to detect contact, acceleration, proximity and temperature. Such artificial skin enables robots to perceive their surroundings in much greater detail and with more sensitivity.

Technical University of Munich researchers designed a system integrating artificial skin with control algorithms, which they used to create the first autonomous humanoid robot with full-body synthetic skin. Researchers at the Technical University of Munich in Germany have designed a system integrating artificial skin with control algorithms, which they used to create the first autonomous humanoid robot with full-body synthetic skin. The skin is composed of hexagonal cells about an inch in diameter, each with a microprocessor and sensors to measure pressure, acceleration, proximity, and temperature. The researchers use an event-based system to track the cells instead of continuous monitoring, with individual cells only sending data when values change; this cuts the processing load by up to 90%. Said the university's Gordon Cheng, "Our system is designed to work trouble-free and quickly with all kinds of robots. Now we're working to create smaller skin cells with the potential to be produced in larger numbers."

TED talks are known to empower us with knowledge and allow us a peak into how smart people think. There has been a huge hype around AI for a few years now and yet, most of us are not sure about what this new technology can do for us? Most often than not we are in fear of the negative impact it can have on our lives. This is due to the ambiguity that surrounds AI. Will it take over my job?

Sensitive synthetic skin enables robots to sense their own bodies and surroundings--a crucial capability if they are to be in close contact with people. Inspired by human skin, a team at the Technical University of Munich (TUM) has developed a system combining artificial skin with control algorithms and used it to create the first autonomous humanoid robot with full-body artificial skin. The artificial skin developed by Prof. Gordon Cheng and his team consists of hexagonal cells about the size of a two-euro coin (i.e. about one inch in diameter). Each is equipped with a microprocessor and sensors to detect contact, acceleration, proximity and temperature. Such artificial skin enables robots to perceive their surroundings in much greater detail and with more sensitivity.

In management, business, economics, scien ce, engineering, and research domains, L arge Scale Global Optimization (LSGO) plays a predominant and vital role. Though LSGO is applied in many of the application domains, it is a very troublesome and a perverse task . The Congress o n Evolutionary Comp utation (CEC) began a n LSGO competition to come up with algorithms with a bunch of standard benchmark unconstrained LS GO functions . Therefore, in this paper, we propos e a hybrid meta - heuristic algorithm, which combines a n I mproved and M odified Harmony Search (IMHS), along with a M odified Differential Evolution (MDE) with an alternate selection strategy . Harmony Search (HS) does the job of exploration and exploitation, and Differe ntial Evolution does the job of giving a perturbation to the exploration of IMHS, as harmony search suffers from being stuck at the basin of local optimal . To judge the performance of the suggested algorithm, we compare the proposed algorithm with ten excellent met a - heuristic algorithms on fifteen LSGO benchmark functions, which have 1000 continuous decision variables, of the CEC 2013 LSGO special session . The experimental results consistently show that our proposed hybrid meta - heuristic performs statistically on par with some algorithms in a few problems, while it turned out to be the best in a couple of problems.

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated machine learning (autoML) has been gaining attention. Here, we apply an autoML library called TPOT which uses a tree-based representation of machine learning pipelines and conducts a genetic-programming based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging datasets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean accuracy error (MAE): $4.612 \pm .124$ years) and a Relevance Vector Regression (MAE $5.474 \pm .140$ years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.

Many systems require optimisation over multiple objectives, where objectives are characteristics of the system such as energy consumed or increase in time to perform the work. Optimisation is performed by selecting the `best' set of input parameters to elicit the desired objectives. However, the parameter search space can often be far larger than can be searched in a reasonable time. Additionally, the objectives are often mutually exclusive -- leading to a decision being made as to which objective is more important or optimising over a combination of the objectives. This work is an application of a Genetic Algorithm to identify the Pareto frontier for finding the optimal parameter sets for all combinations of objectives. A Pareto frontier can be used to identify the sets of optimal parameters for which each is the `best' for a given combination of objectives -- thus allowing decisions to be made with full knowledge. We demonstrate this approach for the HTC-Sim simulation system in the case where a Reinforcement Learning scheduler is tuned for the two objectives of energy consumption and task overhead. Demonstrating that this approach can reduce the energy consumed by ~36% over previously published work without significantly increasing the overhead.

Meta-learning is a paradigm in machine learning which aims to develop models and training algorithms which can quickly adapt to new tasks and data. Our focus in this paper is on meta-learning in reinforcement learning (RL), where data efficiency is of paramount importance because gathering new samples often requires costly simulations or interactions with the real world. A popular technique for RL meta-learning is Model Agnostic Meta Learning (MAML) (Finn et al., 2017, 2018), a model for training an agent (the meta-policy) which can quickly adapt to new and unknown tasks by performing one (or a few) gradient updates in the new environment. We provide a formal description of MAML in Section 2. MAML has proven to be successful for many applications. However, implementing and running MAML continues to be challenging. One major complication is that the standard version of MAML requires estimating second derivatives of the RL reward function, which is difficult when using backpropagation on stochastic policies; indeed, the original implementation of MAML (Finn et al., 2017) did so incorrectly, which spurred the development of unbiased higher-order estimators (DiCE, (Foerster et al., 2018)) and further analysis of the credit assignment mechanism in MAML (Rothfuss et al., 2019).