The growing number of low-power smart devices in the Internet of Things is coupled with the concept of "Edge Computing", that is moving some of the intelligence, especially machine learning, towards the edge of the network. Enabling machine learning algorithms to run on resource-constrained hardware, typically on low-power smart devices, is challenging in terms of hardware (optimized and energy-efficient integrated circuits), algorithmic and firmware implementations. This paper presents FANN-on-MCU, an open-source toolkit built upon the Fast Artificial Neural Network (FANN) library to run lightweight and energy-efficient neural networks on microcontrollers based on both the ARM Cortex-M series and the novel RISC-V-based Parallel Ultra-Low-Power (PULP) platform. The toolkit takes multi-layer perceptrons trained with FANN and generates code targeted at execution on low-power microcontrollers either with a floating-point unit (i.e., ARM Cortex-M4F and M7F) or without (i.e., ARM Cortex M0-M3 or PULP-based processors). This paper also provides an architectural performance evaluation of neural networks on the most popular ARM Cortex-M family and the parallel RISC-V processor called Mr. Wolf. The evaluation includes experimental results for three different applications using a self-sustainable wearable multi-sensor bracelet. Experimental results show a measured latency in the order of only a few microseconds and a power consumption of few milliwatts while keeping the memory requirements below the limitations of the targeted microcontrollers. In particular, the parallel implementation on the octa-core RISC-V platform reaches a speedup of 22x and a 69% reduction in energy consumption with respect to a single-core implementation on Cortex-M4 for continuous real-time classification.

In this post, we will see how to implement the perceptron model using breast cancer data set in python. A perceptron is a fundamental unit of the neural network which takes weighted inputs, process it and capable of performing binary classifications. This is a follow up to my previous post on the Perceptron Model. If you want to skip the theory and jump into code directly click here. In the perceptron model inputs can be real numbers unlike the Boolean inputs in MP Neuron Model.

This project challenges the car racing problem from OpenAI gym environment. The problem is very challenging since it requires computer to finish the continuous control task by learning from pixels. To tackle this challenging problem, we explored two approaches including evolutionary algorithm based genetic multi-layer perceptron and double deep Q-learning network. The result shows that the genetic multi-layer perceptron can converge fast but when training many episodes, double deep Q-learning can get better score. We analyze the result and draw a conclusion that for limited hardware resources, using genetic multi-layer perceptron sometimes can be more efficient.

To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While algorithms have been developed to improve fairness, they typically face at least one of three shortcomings: they are not interpretable, they lose significant accuracy compared to unbiased equivalents, or they are not transferable across models. To address these issues, we propose a geometric method that removes correlations between data and any number of protected variables. Further, we can control the strength of debi-asing through an adjustable parameter to address the tradeoff between model accuracy and fairness. The resulting features are interpretable and can be used with many popular models, such as linear regression, random forest and multilayer perceptrons. The resulting predictions are found to be more accurate and fair than several comparable fair AI algorithms across a variety of benchmark datasets. Our work shows that debiasing data is a simple and effective solution toward improving fairness.

We develop a statistical mechanical approach based on the replica method to study the solution space of deep neural networks. Specifically we analyze the configuration space of the synaptic weights in a simple feed-forward perceptron network within a Gaussian approximation for two scenarios : a setting with random inputs/outputs and a teacher-student setting. By increasing the strength of constraints, i. e. increasing the number of imposed patterns, successive 2nd order glass transition (random inputs/outputs) or 2nd order crystalline transition (teacher-student setting) take place place layer-by-layer starting next to the inputs/outputs boundaries going deeper into the bulk. For deep enough network the central part of the network remains in the liquid phase. We argue that in systems of finite width, weak bias field remain in the central part and plays the role of a symmetry breaking field which connects the opposite sides of the system. In the setting with random inputs/outputs, the successive glass transitions bring about a hierarchical free-energy landscape with ultra-metricity, which evolves in space: it is most complex close to the boundaries but becomes renormalized into progressively simpler one in deeper layers. These observations provide clues to understand why deep neural networks operate efficiently. Finally we present results of a set of numerical simulations to examine the theoretical predictions.

As you know a perceptron serves as a basic building block for creating a deep neural network therefore, it is quite obvious that we should begin our journey of mastering Deep Learning with perceptron and learn how to implement it using TensorFlow to solve different problems. In case you are completely new to deep learning, I would suggest you to go through the previous blog of this Deep Learning Tutorial series to avoid any confusion. Basically, a problem is said to be linearly separable if you can classify the data set into two categories or classes using a single line. On the contrary, in case of a non-linearly separable problems, the data set contains multiple classes and requires non-linear line for separating them into their respective classes. Let us visualize the difference between the two by plotting the graph of a linearly separable problem and non-linearly problem data set:Since, you all are familiar with AND Gates, I will be using it as an example to explain how a perceptron works as a linear classifier.

One way to recognise an object is to study how the echo has been shaped during the interaction with the target. Wideband sonar allows the study of the energy distribution for a large range of frequencies. The frequency distribution contains information about an object, including its inner structure. This information is a key for automatic recognition. The scattering by a target can be quantitatively described by its Form Function. The Form Function can be calculated based on the data of the initial pulse, reflected pulse and parameters of a medium where the pulse is propagating. In this work spherical objects are classified based on their filler material - water or air. We limit the study to spherical 2 layered targets immersed in water. The Form Function is used as a descriptor and fed into a Neural Network classifier, Multilayer Perceptron (MLP). The performance of the classifier is compared with Support Vector Machine (SVM) and the Form Function descriptor is examined in contrast to the Time and Frequency Representation of the echo.

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated sentences, but training typically uses maximum likelihood at the word level. Learning to recognize individual faces from group photos, each captioned with the correct but unordered list of people in it, is another example where a mismatch between training and inference objectives occurs. In both cases, the natural training-time loss would involve a combinatorial problem -- dynamic programming-based global sequence alignment and weighted bipartite graph matching, respectively -- but solutions to combinatorial problems are not differentiable with respect to their input parameters, so surrogate, differentiable losses are used instead. Here, we show how to perform gradient descent over combinatorial optimization algorithms that involve continuous parameters, for example edge weights, and can be efficiently expressed as integer, linear, or mixed-integer linear programs. We demonstrate usefulness of gradient descent over combinatorial optimization in sequence-to-sequence modeling using differentiable encoder-decoder architecture with softmax or Gumbel-softmax, and in weakly supervised learning involving a convolutional, residual feed-forward network for image classification.

Automated classification of metadata of research data by their discipline(s) of research can be used in scientometric research, by repository service providers, and in the context of research data aggregation services. Openly available metadata of the DataCite index for research data were used to compile a large training and evaluation set comprised of 609,524 records, which is published alongside this paper. These data allow to reproducibly assess classification approaches, such as tree-based models and neural networks. According to our experiments with 20 base classes (multi-label classification), multi-layer perceptron models perform best with a f1-macro score of 0.760 closely followed by Long Short-Term Memory models (f1-macro score of 0.755). A possible application of the trained classification models is the quantitative analysis of trends towards interdisciplinarity of digital scholarly output or the characterization of growth patterns of research data, stratified by discipline of research. Both applications perform at scale with the proposed models which are available for re-use.

This post is a part of my forthcoming book on Mathematical foundations of Data Science. In this post, we use the Perceptron algorithm to bridge the gap between high school maths and deep learning. As part of my role as course director of the Artificial Intelligence: Cloud and Edge Computing at the University..., I see more students who are familiar with programming than with mathematics. They have last learnt maths years ago at University. And then, suddenly they find that they encounter matrices, linear algebra etc when they start learning Data Science.