A simple A.I. predictor written in python. This few lines code is a TEXT predictor that works with a 0,1 labeled classifier. The code itself is based on SKLEARN and on a CLASSIFIER previously created, and it analize new piece of text and LABEL them. The classifier gives the EXPERIENCE to the computer in order to let it learn how to takes autonomous decision, so please keep in our mind that the main point to develop a ROBUST A.I. is to build and use a BIG, SPECIFIC and HIGH QUALITY CLASSIFIER!

After preparing training dataset the next step is to train CNN model, earlier we used Caffe training model, but later on switched to Tensorflow since it reduces building training and deploying models with production ready serving platform and supports high level API's like Keras and TFlearn. Keras a high-level neural networks API, written in Python and capable of running on top of either TensorFlow, CNTK, MXNet or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Convolutional Neural Networks (CNN), a technique within the broader Deep Learning field, have been a revolutionary force in Computer Vision applications, especially in the past half-decade or so.

Artificial Intelligence technologies are making a splash across many industry sectors. In this article, we take a brief look at the technologies of Artificial Intelligence in 2019. It is a part of the AI subcategory. This application helps in the conversion of data to text format. And the most important point, it can communicate ideas with accuracy. And this technology can generate market reports and analytical insights.

The app does this by consolidating all of a patient's medical data. Everyone treating the patient can enter information into their file directly from the app, and the app can then send alerts to healthcare workers as soon as signs of a potentially life-threatening problem arise. Streams is currently used under very narrow conditions: only by workers at specific U.K. facilities and only for the detection of acute kidney injury. With Google's full support, though, the app could very well become the go-to medical tool of healthcare professional across the globe. And seemingly nothing would make the DeepMind team happier.

Previous works observed the spectrum of the Hessian of the training loss of deep neural networks. However, the networks considered were of minuscule size. We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate the spectrum of the Hessian of deep nets with tens of millions of parameters. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits 'spiked' behavior, with several outliers isolated from a continuous bulk. However we find that the bulk does not follow a simple Marchenko-Pastur distribution, as previously suggested, but rather a heavier-tailed distribution. Finally, we document the dynamics of the outliers and the bulk with varying sample size.

Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are all relatively small. Meanwhile, most of the previous methods rely on complicated structures with given scarce data, which largely limits the efficacy of the neural models. In this paper, we exploit a new direction named coarse-to-fine task transfer, which aims to leverage knowledge learned from a rich-resource source domain of the coarse-grained AC task, which is more easily accessible, to improve the learning in a low-resource target domain of the fine-grained AT task. To resolve both the aspect granularity inconsistency and feature mismatch between domains, we propose a Multi-Granularity Alignment Network (MGAN). In MGAN, a novel Coarse2Fine attention guided by an auxiliary task can help the AC task modeling at the same fine-grained level with the AT task. To alleviate the feature false alignment, a contrastive feature alignment method is adopted to align aspect-specific feature representations semantically. In addition, a large-scale multi-domain dataset for the AC task is provided. Empirically, extensive experiments demonstrate the effectiveness of the MGAN.

Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we reduce the data preparation cost by leveraging weak supervision in the form of object bounding boxes. To accomplish this, we propose a principled framework that trains a deep convolutional segmentation model that combines a large set of weakly supervised images (having only object bounding box labels) with a small set of fully supervised images (having semantic segmentation labels and box labels). Our framework trains the primary segmentation model with the aid of an ancillary model that generates initial segmentation labels for the weakly supervised instances and a self-correction module that improves the generated labels during training using the increasingly accurate primary model. We introduce two variants of the self-correction module using either linear or convolutional functions. Experiments on the PASCAL VOC 2012 and Cityscape datasets show that our models trained with a small fully supervised set perform similar to, or better than, models trained with a large fully supervised set while requiring ~7x less annotation effort.

Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine hyper-parameter tuning in order to achieve its best performance. This has led to the development of adaptive methods, that claim automatic hyper-parameter tuning. Recently, researchers have studied both algorithmic classes via thoughtful toy problems: e.g., for over-parameterized linear regression, [1] shows that, while SGD always converges to the minimum-norm solution (similar to the case of the maximum margin solution in SVMs that guarantees good prediction error), adaptive methods show no such inclination, leading to worse generalization capabilities. Our aim is to study this conjecture further. We empirically show that the minimum norm solution is not necessarily the proper gauge of good generalization in simplified scenaria, and different models found by adaptive methods could outperform plain gradient methods. In practical DNN settings, we observe that adaptive methods often perform at least as well as SGD, without necessarily reducing the amount of tuning required.

Drug resistance is still a major challenge in cancer therapy. Drug combination is expected to overcome drug resistance. However, the number of possible drug combinations is enormous, and thus it is infeasible to experimentally screen all effective drug combinations considering the limited resources. Therefore, computational models to predict and prioritize effective drug combinations is important for combinatory therapy discovery in cancer. In this study, we proposed a novel deep learning model, AuDNNsynergy, to prediction drug combinations by integrating multi-omics data and chemical structure data. In specific, three autoencoders were trained using the gene expression, copy number and genetic mutation data of all tumor samples from The Cancer Genome Atlas. Then the physicochemical properties of drugs combined with the output of the three autoencoders, characterizing the individual cancer cell-lines, were used as the input of a deep neural network that predicts the synergy value of given pair-wise drug combinations against the specific cancer cell-lines. The comparison results showed the proposed AuDNNsynergy model outperforms four state-of-art approaches, namely DeepSynergy, Gradient Boosting Machines, Random Forests, and Elastic Nets. Moreover, we conducted the interpretation analysis of the deep learning model to investigate potential vital genetic predictors and the underlying mechanism of synergistic drug combinations on specific cancer cell-lines.

Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively in machine learning, until rather recently. In this article we show a general way to incorporate symmetries into machine learning models. We demonstrate this with a detailed analysis on a rather simple real world machine learning system - a neural network for classifying handwritten digits, lacking bias terms for every neuron. We demonstrate that ignoring symmetries can have dire over-fitting consequences, and that incorporating symmetry into the model reduces over-fitting, while at the same time reducing complexity, ultimately requiring less training data, and taking less time and resources to train.