IT and AI
1.8K views | +4 today
Follow
Your new post is loading...
Your new post is loading...
Scooped by Jaime Camacaro
Scoop.it!

Getting Value from Machine Learning Isn’t About Fancier Algorithms — It’s About Making It Easier to Use

Getting Value from Machine Learning Isn’t About Fancier Algorithms — It’s About Making It Easier to Use | IT and AI | Scoop.it
We built a model to help project managers meet their deadlines.
more...
No comment yet.
Rescooped by Jaime Camacaro from artificial intelligence for students
Scoop.it!

Getting Value from Machine Learning Isn’t About Fancier Algorithms — It’s About Making It Easier to Use

Getting Value from Machine Learning Isn’t About Fancier Algorithms — It’s About Making It Easier to Use | IT and AI | Scoop.it
We built a model to help project managers meet their deadlines.

Via Scott Turner
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Tensor Comprehensions in PyTorch

Tensor Comprehensions (TC) is a tool that lowers the barrier for writing high-performance code. It generates GPU code from a simple high-level language and autotunes the code for specific input sizes. We highly recommend reading the Tensor Comprehensions blogpost first. If you ran into any of the following scenarios, TC is a useful tool for you.
1
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Using Machine Learning Agents in a real game: a beginner’s guide – Unity Blog

Using Machine Learning Agents in a real game: a beginner’s guide – Unity Blog | IT and AI | Scoop.it
My name is Alessia Nigretti and I am a Technical Evangelist for Unity. My job is to introduce Unity’s new features to developers. My fellow evangelis
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Scant Evidence of Power Laws Found in Real-World Networks

Scant Evidence of Power Laws Found in Real-World Networks | IT and AI | Scoop.it
A new study challenges one of the most celebrated and controversial ideas in network science.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Geometric Deep Learning on Graphs and Manifolds on

This is "Geometric Deep Learning on Graphs and Manifolds" by TechTalksTV on Vimeo, the home for high quality videos and the people who love them.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

DeepLeague: leveraging computer vision and deep learning on the League of Legends mini map + giving…

Note: All of this is free + open-source. I explain all the gritty technical details in Part 2 of this post which you can find here. Feel free to contact me at anytime if you have questions. Note 2…
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

[1802.04730] Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions

more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Cloud TPU machine learning accelerators now available in beta

Cloud TPU machine learning accelerators now available in beta | IT and AI | Scoop.it
By John Barrus, Product Manager for Cloud TPUs, Google Cloud and Zak Stone, Product Manager for TensorFlow and Cloud TPUs, Google Brai
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

hiranumn/IntegratedGradients: Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.

hiranumn/IntegratedGradients: Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework. | IT and AI | Scoop.it
IntegratedGradients - Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Artificial Intelligence: How We Help Machines Learn (Paid Post by Facebook From The New York Times)

Artificial Intelligence: How We Help Machines Learn (Paid Post by Facebook From The New York Times) | IT and AI | Scoop.it
How do we teach A.I. to be intelligent?
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Autonomous Reconstruction of Unknown Indoor Scenes Guided by Time-varying Tensor Fields 

Autonomous Reconstruction of Unknown Indoor Scenes Guided by Time-varying Tensor Fields  | IT and AI | Scoop.it
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

NFL teams with AWS on statistics package driven by machine learning

NFL teams with AWS on statistics package driven by machine learning | IT and AI | Scoop.it
The NFL is joining Major League Baseball as an AWS customer, announcing a deal today to provide real-time statistics running on AWS. The tool is part of the..
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

[1803.01271] An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

For most deep learning practitioners, sequence modeling is synonymous with recurrent networks. Yet recent results indicate that convolutional architectures can outperform recurrent networks on tasks such as audio synthesis and machine translation. Given a new sequence modeling task or dataset, which architecture should one use? We conduct a systematic evaluation of generic convolutional and recurrent architectures for sequence modeling. The models are evaluated across a broad range of standard tasks that are commonly used to benchmark recurrent networks. Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory. We conclude that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutional networks should be regarded as a natural starting point for sequence modeling tasks.
1
more...
No comment yet.
Rescooped by Jaime Camacaro from artificial intelligence for students
Scoop.it!

Machine Learning Crash Course  | 

Machine Learning Crash Course  |  | IT and AI | Scoop.it
Educational resources for machine learning

Via Scott Turner
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Interactive Workflows for C++ with Jupyter –

Scientists, educators and engineers not only use programming languages to build software systems, but also in interactive workflows, using the tools available to explore a problem and reason about…
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native - Stefano J. Attardi

How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native - Stefano J. Attardi | IT and AI | Scoop.it
UI Engineering and Design consultant, specializing in React and React performance. Previously at Facebook and Storehouse. Winner of the first Node.js Knockout with Swarmation.com.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

A detailed example of data generators with Keras

A detailed example of data generators with Keras | IT and AI | Scoop.it
Blog of Shervine Amidi, Graduate Student at Stanford University.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Introduction to Learning to Trade with Reinforcement Learning –

Introduction to Learning to Trade with Reinforcement Learning – | IT and AI | Scoop.it
Thanks a lot to @aerinykim, @suzatweet and @hardmaru for the useful feedback! The academic Deep Learning research community has largely stayed away from the financial markets. Maybe that’s be…
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

How to predict Quora Question Pairs using Siamese Manhattan LSTM

The article is about Manhattan LSTM (MaLSTM) — a Siamese deep network and its appliance to Kaggle’s Quora Pairs competition.
I will do my best to explain the network and go through the Keras code (if…
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

How to build your own AlphaZero AI using Python and Keras

The codebase contains a replica of the AlphaZero methodology, built in Python and Keras. Gain a deeper understanding of how AlphaZero works and adapt the code to plug in new games.
more...
No comment yet.
Scooped by Jaime Camacaro
Scoop.it!

Building a Deep Neural Network to play FIFA 18 – Towards Data Science

A.I. bots in gaming are usually built by hand-coding a bunch of rules that impart game-intelligence. For the most part, this approach does a fairly good job of making the bot imitate human-like…
more...
No comment yet.