IN CASE YOU MISSED IT!

BigData News Friday, March 30 Virtual agent, Video game doom, Repux tokens & more…

[vc_row][vc_column][vc_column_text]

BigData News TLDR / Table of Contents

[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”Watch-a-Computer-Learn-to-Play-Doom-Inside-a-Dream”][vc_column width=”1/2″][vc_separator][vc_column_text]

Watch a Computer Learn to Play ‘Doom’ Inside a Dream

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • Case in point: Researchers David Ha (of Google Brain, the search giants machine learning wing) and Jrgen Schmidhuber were able to get a machine to hallucinate, as they put it, its own idea of what the 1993 video game Doom looks like.
  • The machine learning set up for this task had three components: First, a model that comes up with a compressed version of the game environment based on a snapshot (like a low bitrate MP3 or deep fried JPEG), and then another model that takes that information to output a probability…
  • All of these machine learning models, plugged into one another, allow a virtual agent to perceive a game world and play within it properly.
  • To do just this, Ha and Schmidhuber got their prediction model to sample its own predictions of the game state as a source for further predictions, creating an entirely imagined idea of the game world based on the real thing.
  • The model was also given the ability to predict if the player dies in the next frame in addition to predicting the next frame itself, creating the conditions for a virtual agent to play and train inside this dream state that probabilistically recreates a machines idea of Doom (technically, a…

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: virtual agent, video game Doom, bong water fantasy, Dr. Daniel Erlacher, lucid dreaming state—the[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]Watch a Computer Learn to Play ‘Doom’ Inside a Dream – Motherboard[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”How-to-buy-with-BTC-“][vc_column width=”1/2”][vc_separator][vc_column_text]

How to buy with BTC ?

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • To take part in RepuX Token Sale you have to find BUY NOW WITH 20% BONUS form on our repux.io page.
  • Click the link in the email that is marked Sign in with magic link to RepuX.
  • Then you will be transferred to your account on RepuX site.
  • Your account contains information such as: – – To complete PAYMENT DETAILS you have to fill in: – – For BTC – if you have an ETH wallet for which you want to receive REPUX Tokens, enter the address of your ETH wallet.
  • Just press the green BUY TOKENS button which is displayed on your RepuX account.

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: REPUX Tokens, RepuX Token Sale, ETH wallet, BUY TOKENS, repux.io page[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]How to buy with BTC ? | RepuX Help Center[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”25-Open-Datasets-for-Deep-Learning-Every-Data-Scientist-Must-Work-With”][vc_column width=”1/2″][vc_separator][vc_column_text]

25 Open Datasets for Deep Learning Every Data Scientist Must Work With

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • It has several features: – – Number of Records:330K images, 80 object categories, 5 captions per image, 250,000 people with key points – – ImageNet is a dataset of images that are organized according to the WordNet hierarchy.
  • Some of the interesting features of this dataset are: – – Number of Records:265,016 images, at least 3 questions per image, 10 ground truth answers per question – – SOTA :Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge – – This is a real-world image dataset…
  • It is similar to the MNIST dataset mentioned in this list, but has more labelled data (over 600,000 images).
  • Number of Records:681,288 posts with over 140 million words – – This dataset consists of training data for four European languages.
  • Number of Records: 19,906 images in the training set and 6636 in the test set – – SOTA: Hands on with Deep Learning Solution for Age Detection Practice Problem – – This dataset consists of more than 8000 sound excerpts of urban sounds from 10 classes.

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: dataset, SOTA, speaker identification dataset, open dataset, [/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]25 Open Datasets for Deep Learning Every Data Scientist Must Work With[/vc_column_text][/vc_column][/vc_row]