Pseudorehearsal Approach for Incremental Learning of Deep Convolutional Neural Networks


Deep Convolutional Neural Networks, like most connectionist models, suffers from catastrophic forgetting while training for a new, unknown task. One of the simplest solutions to this issue is adding samples of previous data, with the drawback of increasingly having to store training data; or generating patterns that evoke similar responses of the previous task. We propose a model using a Recurrent Neural Network-based image generator in order to provide a Deep Convolutional Network a limited number of samples for new training data. Simulation results shows that our proposal is able to retain previous knowledge whenever some few pseudo-samples of previously recorded patterns are generated. Despite having lower performance than giving the network samples of the real dataset, this model is more biologically plausible and might help to reduce the need of storing previously trained data on bigger-scale classification classification models.

NASA's Space AI Hunts Exoplanets, Not Humans -- Yet


When it comes to artificial intelligence, NASA and other space agencies are nowhere near building a "Terminator" in space. So, you can rest easy -- Arnold Schwarzenegger isn't about to hunt you down because you're leading a rebellion against the machines. Artificial intelligence is in its infancy, but scientists have used it to find alien planets, classify galaxies and create spacecraft capable of dodging debris. But some critics, like SpaceX founder Elon Musk and the renowned physicist Stephen Hawking (recently deceased), have warned that artificial intelligence could be dangerous if left unchecked. While AI is a popular theme in space exploration, its use (and misuse) has been discussed by several people in other applications as well.

The Current Best of Universal Word Embeddings and Sentence Embeddings


Word and sentence embeddings have become an essential part of any Deep-Learning-based natural language processing systems. They encode words and sentences in fixed-length dense vectors to drastically improve the processing of textual data. A huge trend is the quest for Universal Embeddings: embeddings that are pre-trained on a large corpus and can be plugged in a variety of downstream task models (sentimental analysis, classification, translation…) to automatically improve their performance by incorporating some general word/sentence representations learned on the larger dataset. Transfer learning has been recently shown to drastically increase the performance of NLP models on important tasks such as text classification. Go check the very nice work of Jeremy Howard and Sebastian Ruder (ULMFiT) to see it in action.

Machine Learning Optimization Using Genetic Algorithm


In this course, you will learn what hyperparameters are, what Genetic Algorithm is, and what hyperparameter optimization is. In this course, you will apply Genetic Algorithm to optimize the performance of Support Vector Machines and Multilayer Perceptron Neural Networks. Hyperparameter optimization will be done on two datasets, a regression dataset for the prediction of cooling and heating loads of buildings, and a classification dataset regarding the classification of emails into spam and non-spam. The SVM and MLP will be applied on the datasets without optimization and compare their results to after their optimization. By the end of this course, you will have learnt how to code Genetic Algorithm in Python and how to optimize your Machine Learning algorithms for maximal performance.

Classification-Based Machine Learning for Finance


Finally, a comprehensive hands-on machine learning course with specific focus on classification based models for the investment community and passionate investors. In the past few years, there has been a massive adoption and growth in the use of data science, artificial intelligence and machine learning to find alpha. However, information on and application of machine learning to investment are scarce. This course has been designed to address that. It is meant to spark your creative juices and get you started in this space.

Practical Machine Learning Coursera


One of the most common tasks performed by data scientists and data analysts are prediction and machine learning. This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. The course will provide basic grounding in concepts such as training and tests sets, overfitting, and error rates. The course will also introduce a range of model based and algorithmic machine learning methods including regression, classification trees, Naive Bayes, and random forests. The course will cover the complete process of building prediction functions including data collection, feature creation, algorithms, and evaluation.

From 0 to 1: Machine Learning, NLP & Python-Cut to the Chase


Prerequisites: No prerequisites, knowledge of some undergraduate level mathematics would help but is not mandatory. Working knowledge of Python would be helpful if you want to run the source code that is provided. Taught by a Stanford-educated, ex-Googler and an IIT, IIM - educated ex-Flipkart lead analyst. This team has decades of practical experience in quant trading, analytics and e-commerce. The course is shy but confident: It is authoritative, drawn from decades of practical experience -but shies away from needlessly complicating stuff.

A Comparative Study of Classification Techniques in Data Mining Algorithms


Classification is used to find out in which group each data instance is related within a given dataset. It is used for classifying data into different classes according to some constrains. Several major kinds of classification algorithms including C4.5, ID3, k-nearest neighbor classifier, Naive Bayes, SVM, and ANN are used for classification. Generally a classification technique follows three approaches Statistical, Machine Learning and Neural Network for classification. While considering these approaches this paper provides an inclusive survey of different classification algorithms and their features and limitations.

Microsoft and OS hack


The hack, featuring software engineers from Microsoft who had travelled from across Europe and Africa to work with OS's machine learning team, used the city of Hull as a testbed. The trained machine model finished the week by correctly identifying 87% of the roof types it was shown. In its training the model was shown 500 flat roofs and 500 hipped/gabled roofs, set a confidence limit of 90%, which means it must be 90% confident or more for its assessment to count. Isabel Sargent, Senior Research and Development Scientist at OS, says: "Thanks to the excellence of the Microsoft team we have been able to work out together how to stream this machine captured data into our database for if and when we're ready to put machine learning into production. It's already very accurate, going from zero to 87% accuracy in just one week, but we need to increase its success rate.

Identifying Patterns in Medical Records through Latent Semantic Analysis

Communications of the ACM

Mountains of data are constantly being accumulated, including in the form of medical records of doctor visits and treatments. The question is what actionable information can be gleaned from it beyond a one-time record of a specific medical examination. Arguably, if one were to combine the data in a large corpus of many patients suffering from the same condition, then overall patterns that apply beyond a specific instance of a specific doctor visit might be observed. Such patterns might reveal how medical conditions are related to one another over a broad set of patients, as well as how these conditions might be related to the International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) of the Centers for Disease Control and Prevention (CDC) Classification of Diseases, Functioning, and Disability codes (henceforth, ICD codesa). Conceivably, applying such a method to a large dataset could even suggest new avenues of medical and public health research by identifying new associations, along with the relative strength of the associations compared to other associations.