Deep learning is a sub-category within machine learning and artificial intelligence. It is inspired by and based on the model of the human brain to create artificial neural networks for machines. Deep learning will allow machines and devices to function in some ways as humans do.
Dr. Rodrigo Agundez of GoDataDriven is co-author of this article and very enthusiastic about the improvements that deep learning can offer. He’s been involved in the data science and analysis field for…Continue
Added by Ronald van Loon on May 7, 2018 at 11:00pm — No Comments
Machine learning and artificial intelligence (AI) are all the rage these days — but with all the buzzwords swirling around them, it's easy to get lost and not see the difference between hype and reality. For example, just because an algorithm is used to calculate information doesn’t mean the label…Continue
Sometimes when dealing with performance metrics, there are contradictory signals. For instance, although both are desirable, it is common for efficiency and efficacy to be in opposition. An agent in a call centre can handle lots of calls while at the same time getting few sales; this is especially true if the agent’s main objective is to do lots of calls. This is a highly efficient person albeit unsuccessful in terms of expanding the business. Conversely, another agent by spending a…Continue
Added by Don Philip Faithful on May 6, 2018 at 3:30am — No Comments
Monday newsletter published by Data Science Central. Previous editions can be found here. The contribution flagged with a + is our selection for the picture of the week.
Added by Vincent Granville on May 5, 2018 at 6:30am — No Comments
This is a quote by George E Box. Share if you like it.
In short, all models are approximations. All models are wrong, but some are useful. George E Box (18 October 1919 – 28 March 2013) was a British statistician, who worked in the areas of quality control, time-series analysis, design of experiments, and Bayesian inference. He has been called "one of the great statistical minds of the 20th…Continue
Added by Vincent Granville on May 4, 2018 at 10:28am — No Comments
I recently created a ‘particle optimizer’ and published a pip python package called kernelml. The motivation for making this algorithm was to give analysts and data scientists a generalized machine learning algorithm for complex loss functions and non-linear coefficients. The optimizer uses a combination of simple machine learning and probabilistic simulations to search for optimal parameters using a loss function, input and output matrices, and (optionally) a random…Continue
Share your knowledge with other professionals, be respected as an expert in the leading community for data science, stats, BI, operations research, and machine learning practitioners. Or find answers to your business, technical, or career questions. We have thousands of questions posted in our revamped forum section, covering all topics, and usually related to applications: You can reply, contact the authors, post a comment, or ask a new question.
Lists of 160 popular questions (with…Continue
Added by Vincent Granville on May 4, 2018 at 8:30am — No Comments
When a systems integrator selects a data integration tool, it needs to consider a number of selection criteria.
A key criterion for vendor selection is systems compatibility.
The selected tool must foremost be able to interact with the…Continue
Here is our selection of featured articles and resources posted since Monday:
Added by Vincent Granville on May 3, 2018 at 8:30am — No Comments
When the first release of Spark became available in 2014, Hadoop had already enjoyed several years of growth since 2009 onwards in the commercial space. Although Hadoop solved a major hurdle in analyzing large terabyte-scale datasets efficiently, using distributed computing methods that were broadly accessible, it still had shortfalls that hindered its wider acceptance.
Limitations of Hadoop
A few of the common…
Added by Packt Publishing on May 3, 2018 at 1:30am — No Comments
The age of Artificial Intelligence (AI) is almost upon us. Rapid developments in machine learning have allowed us to build better, smarter machines that are capable of making decisions and handling tasks similar to humans.
Some of these developments…Continue
Added by Ronald van Loon on May 2, 2018 at 10:00pm — No Comments
Enterprises are learning fast about the relevance and use of AI and Cognitive Computing platforms. Before adopting AI and Cognitive Computing platforms, enterprises must focus on designing the right strategy for their business. A data-driven strategy is very important to derive the maximum benefit from the…Continue
Added by Dileep Srinivasan on May 2, 2018 at 5:30pm — No Comments
This is a popular question recently posted on Quora, with my answer viewed more than 8,000 times so far. I am re-posting it here. This post is much more detailed than my initial answer.
My answer may appear sarcastic, after all, I am a math PhD and have published in journals such as Journal of Number Theory. But I left academia long ago, yet still doing what I think is ground-breaking research in…Continue
What I discussed here is not only the math derivation which has usually been ignored in decision tree, but also the following question: what does the cross-entropy really means for decision tree, and how will it lead to over-fitting.
The expected cross-entropy is usually used as the cost function for the decision tree. You can find the definition of expected cross entropy everywhere. Let's start our story from a simple example.
Added by Xiaoli Chen on May 2, 2018 at 9:00am — No Comments
Guest blog post by David Enríquez Arriano. For more information or to get higher pictures resolution, contact the author (see contact information at the bottom of this article.)
This is a different approach to solve the AI problem. It is a cognitive math based on pyramids built with self-programming logic gates through learning.
A Boolean polynomial associated with a given truth table can be…Continue
Added by Vincent Granville on May 2, 2018 at 6:30am — No Comments
A machine learning solution can be broadly divided into 3 parts. A typical ML exercise would involve experimentation and iteration of all the 3 parts together and/or 1 of the 3 parts before arriving at a solution.
1. Pre-Processing: Preparation of data for modeling.You are the best judge of what needs to be done, but here are some considerations:
Added by Uday Krishna on May 2, 2018 at 4:30am — No Comments
At a conference I attended a few years ago, a data scientist on a round table discussion replied to a question of what she considered the most important mathematical function in her work with: "the division operator". That clever response provided grist for my later answer to a similar question on…Continue
Summary: Our starting assumption that sequence problems (language, speech, and others) are the natural domain of RNNs is being challenged. Temporal Convolutional Nets (TCNs) which are our workhorse CNNs with a few new features are outperforming RNNs on major applications today. Looks like RNNs may well be history.
At the Mobile World Congress, MasterCard recently announced that it was teaming up with Facebook to provide small businesses in Africa and Asia with an affordable and simple on-ramp for accepting mobile payments.
The partnership will help unbanked retailers and merchants in the regions open bank accounts…Continue
Added by Deena Zaidi on April 30, 2018 at 9:30am — No Comments