geoopt/geoopt

#artificialintelligence

Make sure you have pytorch 1.1.0 The preferred way to install geoopt will change once stable project stage is achieved. Now, pypi is behind master as we actively develop and implement new features. Work is in progress but you can already use this. Note that API might change in future releases.


End to End Image Classification project using TensorFlow

#artificialintelligence

The os library gives us access to the file system, and the zipfile library allows us to unzip the data. Convolutions narrow down the content of the image to focus on specific details. It takes longer to run the model, but has a huge impact on accuracy. We add convolutional layers, and flatten the final result to feed into the densely connected layers. As this is a 2 class classification problem, we use the Sigmoid function.


Money Talks: Drone Investment Trends Update - Drone Industry Insights

#artificialintelligence

Earlier this month the thermal imagery manufacturer FLIR bought the UAV developer Aeryon Labs for $200 million, beating their previous record in publicly disclosed drone investments of $134M. This has been yet another signal that even though the drone industry suffered some hard hits in 2018, the period of consolidation, larger investments and serious R&D advances is ahead. In fact, if one were to look at merely the investment figures for 2018, it wouldn't even be that easy to tell that the drone industry struggled. Records were set, partnerships formed, and accelerators continued to support exceptional start-ups. A total of $702 million was invested into the drone industry in 2018 (up from $625M in 2017), $483 million of which was funnelled into the top 20 drone deals.


State of the Art Model Deployment

#artificialintelligence

The normal life cycle of a machine learning model includes several stages, see Figure 1. There are countless online courses and articles about preparing the data and building models but there is much less material about model deployment. Yet, it is precisely at this stage where all the hard work of data preparation and model building starts to pay off. This is where models are used to score (or get predictions for) new cases and extract the benefits. My intent here is to fill this gap, so that you will be fully prepared to deploy your model using time tested resources.


The FCA and the Bank of England find that two-thirds of UK banks and financial service firms use machine learning

#artificialintelligence

Machine learning technology is poised to be huge thing in financial services. In fact, two-thirds of UK-based firms are already using it. That is according to two of the UK's top financial regulators. The Financial Conduct Authority (FCA) and the Bank of England have taken a deep dive into how the financial services industry in the country is using machine learning. The research is based on a survey sent out to 300 firms, including banks, credit brokers, e-money institutions, financial market infrastructure firms, investment managers, insurers, non-bank lenders and principal trading firms.


KNN visualization in just 13 lines of code

#artificialintelligence

Let's play around with datasets to visualize how the decision boundary changes as'k' changes. Let's have a quick review… K Nearest Neighbor(KNN) algorithm is a very simple, easy to understand, versatile and one of the topmost machine learning algorithms. In k-NN classification, the output is a class membership. An object is classified by a plurality vote of its neighbours, with the object being assigned to the class most common among its k nearest neighbours (k is a positive integer, typically small). If k 1, then the object is simply assigned to the class of that single nearest neighbour.


Time Series Analysis in Python 2019

#artificialintelligence

Understand the fundamental assumptions of time series data and how to take advantage of them. Transforming a data set into a time-series. Start coding in Python and learn how to use it for statistical analysis. Carry out time-series analysis in Python and interpreting the results, based on the data in question. Examine the crucial differences between related series like prices and returns.


Analysing Machine Learning Models with Imandra

#artificialintelligence

The vast majority of work within formal methods (the area of computer science that reasons about hardware and software as mathematical objects in order to prove they have certain properties) has involved analysing models that are fully specified by the user. More and more, however, critical parts of algorithmic pipelines are constituted by models that are instead learnt from data using artificial intelligence (AI). The task of analysing these kinds of models presents fresh challenges for the formal methods community and has seen exciting progress in recent years. While scalability is still an important, open research problem -- with state-of-the-art machine learning (ML) models often having millions of parameters --in this post we give an introduction to the paradigm by analysing two simple yet powerful learnt models using Imandra, a cloud-native automated reasoning engine bringing formal methods to the masses! Verifying properties of learnt models is a difficult task, but is becoming increasingly important in order to make sure that the AI systems using such models are safe, robust, and explainable.


Artificial Intelligence Predicts El Niño

#artificialintelligence

Worldwide sea temperature recordings are only available from 1871, and for an artificial intelligence system this is very little data to learn from.


Artificial Intelligence to improve tea quality and health of workers in Assam

#artificialintelligence

GUWAHATI: A Karnataka-born NRI's company will use Artificial Intelligence (AI) to improve the quality of tea and the health of tea workers in tea-rich …