The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter optimization algorithm called BOSS. Empirical studies validate our theoretical arguments of SS and demonstrate the superior performance of BOSS on a number of applications, including Neural Architecture Search (NAS), Data Augmentation (DA), Object Detection (OD), and Reinforcement Learning (RL).

The use of black-box optimization for the design of new biological sequences is an emerging research area with potentially revolutionary impact. The cost and latency of wet-lab experiments requires methods that find good sequences in few experimental rounds of large batches of sequences--a setting that off-the-shelf black-box optimization methods are ill-equipped to handle. We find that the performance of existing methods varies drastically across optimization tasks, posing a significant obstacle to real-world applications. To improve robustness, we propose Population-Based Black-Box Optimization (P3BO), which generates batches of sequences by sampling from an ensemble of methods. The number of sequences sampled from any method is proportional to the quality of sequences it previously proposed, allowing P3BO to combine the strengths of individual methods while hedging against their innate brittleness. Adapting the hyper-parameters of each of the methods online using evolutionary optimization further improves performance. Through extensive experiments on in-silico optimization tasks, we show that P3BO outperforms any single method in its population, proposing higher quality sequences as well as more diverse batches. As such, P3BO and Adaptive-P3BO are a crucial step towards deploying ML to real-world sequence design.

An alternative to current mainstream preprocessing methods is proposed: Value Selection (VS). Unlike the existing methods such as feature selection that removes features and instance selection that eliminates instances, value selection eliminates the values (with respect to each feature) in the dataset with two purposes: reducing the model size and preserving its accuracy. Two probabilistic methods based on information theory's metric are proposed: PVS and P + VS. Extensive experiments on the benchmark datasets with various sizes are elaborated. Those results are compared with the existing preprocessing methods such as feature selection, feature transformation, and instance selection methods. Experiment results show that value selection can achieve the balance between accuracy and model size reduction.

Smart FinTech has emerged as a new area that synthesizes and transforms AI and finance, and broadly data science, machine learning, economics, etc. Smart FinTech also transforms and drives new economic and financial businesses, services and systems, and plays an increasingly important role in economy, technology and society transformation. This article presents a highly summarized research overview of smart FinTech, including FinTech businesses and challenges, various FinTech-associated data and repositories, FinTech-driven business decision and optimization, areas in smart FinTech, and research methods and techniques for smart FinTech.

The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state of the art automatic methods exist that make the search for a good learning rate easier. While these techniques are effective and have yielded good results over the years, they are general solutions. This means the optimization of learning rate for specific network topologies remains largely unexplored. This work presents AutoLR, a framework that evolves Learning Rate Schedulers for a specific Neural Network Architecture using Structured Grammatical Evolution. The system was used to evolve learning rate policies that were compared with a commonly used baseline value for learning rate. Results show that training performed using certain evolved policies is more efficient than the established baseline and suggest that this approach is a viable means of improving a neural network's performance.

Developing secure machine learning models from adversarial examples is challenging as various methods are continually being developed to generate adversarial attacks. In this work, we propose an evolutionary approach to automatically determine Image Processing Techniques Sequence (IPTS) for detecting malicious inputs. Accordingly, we first used a diverse set of attack methods including adaptive attack methods (on our defense) to generate adversarial samples from the clean dataset. A detection framework based on a genetic algorithm (GA) is developed to find the optimal IPTS, where the optimality is estimated by different fitness measures such as Euclidean distance, entropy loss, average histogram, local binary pattern and loss functions. The "image difference" between the original and processed images is used to extract the features, which are then fed to a classification scheme in order to determine whether the input sample is adversarial or clean. This paper described our methodology and performed experiments using multiple data-sets tested with several adversarial attacks. For each attack-type and dataset, it generates unique IPTS. A set of IPTS selected dynamically in testing time which works as a filter for the adversarial attack. Our empirical experiments exhibited promising results indicating the approach can efficiently be used as processing for any AI model.

We apply the algorithm Neuroevolution learning literature [5, 6]. of Augmenting Topologies (NEAT) which has not been widely In this paper, we describe development and application of a applied generally in the credit evaluation domain. In addition to technique for learning online (or frequently updated) credit scoring comparing the methodology with other widely applied machine models as new data is read record by record. We describe the learning techniques, we develop and evaluate several approach developed as Online NEAT for Credit Scoring. The enhancements to the algorithm which make it suitable for the approach applies neuro-evolution, a technique that combines neural particular aspects of online learning that are relevant in the networks with evolutionary computation [7].

We combine momentum from machine learning with evolutionary dynamics, where momentum can be viewed as a simple mechanism of intergenerational memory. Using information divergences as Lyapunov functions, we show that momentum accelerates the convergence of evolutionary dynamics including the replicator equation and Euclidean gradient descent on populations. When evolutionarily stable states are present, these methods prove convergence for small learning rates or small momentum, and yield an analytic determination of the relative decrease in time to converge that agrees well with computations. The main results apply even when the evolutionary dynamic is not a gradient flow. We also show that momentum can alter the convergence properties of these dynamics, for example by breaking the cycling associated to the rock-paper-scissors landscape, leading to either convergence to the ordinarily non-absorbing equilibrium, or divergence, depending on the value and mechanism of momentum.

This top S&P 500 stocks forecast is designed for investors and analysts who need predictions for the whole S&P 500. Package Name: Top S&P 500 Stocks Recommended Positions: Long Forecast Length: 3 Months (4/1/2020 – 7/1/2020) I Know First Average: 32.03% The greatest return came from ABMD at 75.82%. NVDA and ETFC also performed well for this time horizon with returns of 44.61% and 42.98%, respectively. The overall average return in this Top S&P 500 Stocks package was 32.03%, providing investors with a 11.47% premium over the S&P 500's return of 20.56% during the same period.

This stock scanner is part of the Risk-Conscious Package, as one of I Know First's equity research solutions. We determine our aggressive stock picks by screening our algorithm daily for higher volatility stocks that present greater opportunities but are also riskier. Package Name: Aggressive Stocks Forecast Recommended Positions: Long Forecast Length: 3 Months (4/1/2020 – 7/1/2020) I Know First Average: 100.66% The highest trade return came from NVAX, at 486.89%. NLS and DPW followed with returns of 259.77% and 213.26% for the 3 Months period.