#a_fast, unsupervised approach
for medical concept extraction

#paper
----------
@machinelearning_tuts

#Towards a Multi-agent System for Medical Records Processing and
Knowledge Discovery
#paper
----------
@machinelearning_tuts

#advance_in_computational_intelligence
#paper
----------
@machinelearning_tuts

#Learning_Love Data Science
----------
@machinelearning_tuts

#Python_for_Data_Analysis
#book
----------
@machinelearning_tuts

#Artificial Intelligence A Modern Approach
#book
----------
@machinelearning_tuts

#python_power
#book
----------
@machinelearning_tuts

https://instagram-engineering.com/lessons-learned-at-instagram-stories-and-feed-machine-learning-54f3aaa09e56
----------
@machinelearning_tuts

https://towardsdatascience.com/10-data-science-tools-i-explored-in-2018-d8226f99f342
----------
@machinelearning_tuts

❄️ Welcome to "The GAN Zoo"
https://github.com/hindupuravinash/the-gan-zoo
----------
@machinelearning_tuts

#resources
https://www.analyticsindiamag.com/the-best-resources-for-learning-deep-learning-for-beginners
----------
@machinelearning_tuts

پنج الگوريتم خوشه بندي كه هر ديتاساينتيست بايد بداند
https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68
----------
@machinelearning_tuts

This is a passenger drone of the future.
----------
@machinelearning_tuts

Top 10 #deeplearning research papers as per this website
https://lnkd.in/dPYayt9

Of course the choice remains biased but we do like these besides a few hundred other papers.

Remember, it is not the popular but the meaningful and industry relevant research that is worth paying attention to.

Here's the list:

1. Universal Language Model Fine-tuning for Text Classification
https://lnkd.in/dhj5SyM

2. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
https://lnkd.in/d44kt3Q

3. Deep Contextualized Word Representations
https://lnkd.in/dkP68Fb

4. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
https://lnkd.in/dAhYzge

5. Delayed Impact of Fair Machine Learning
https://lnkd.in/dvTvG2s

6. World Models

7. Taskonomy: Disentangling Task Transfer Learning
https://lnkd.in/dYxMjAd

8. Know What You Don’t Know: Unanswerable Questions for SQuAD
https://lnkd.in/d--grME

9. Large Scale GAN Training for High Fidelity Natural Image Synthesis
https://lnkd.in/dY6psf4

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://lnkd.in/dgtnD7n
#machinelearning #research #deeplearning #artificialintelligence

----------
@machinelearning_tuts

#datascience #machinelearning #learning #beginner #python
Learn Python in 30 days.
https://www.datasciencecentral.com/m/blogpost?id=6448529:BlogPost:792505
----------
@machinelearning_tuts

Deep Learning in Software Engineering

--Abstract
Recent years, deep learning is increasingly prevalent in the field ofSoftware Engineering (SE). However, many open issues still remain to beinvestigated. How do researchers integrate deep learning into SE problems?Which SE phases are facilitated by deep learning? Do practitioners benefit fromdeep learning? The answers help practitioners and researchers develop practicaldeep learning models for SE tasks. To answer these questions, we conduct abibliography analysis on 98 research papers in SE that use deep learningtechniques. We find that 41 SE tasks in all SE phases have been facilitated bydeep learning integrated solutions. In which, 84.7% papers only use standarddeep learning models and their variants to solve SE problems. Thepracticability becomes a concern in utilizing deep learning techniques. How toimprove the effectiveness, efficiency, understandability, and testability ofdeep learning based solutions may attract more SE researchers in the future.

2018-05-13T06:01:39Z

@machinelearning_tuts
@selfdrivecar
@autonomousvehicle
----------
Link : http://arxiv.org/abs/1805.04825v1

Deep Learning: Computational Aspects

--Abstract
In this article we review computational aspects of Deep Learning (DL). Deeplearning uses network architectures consisting of hierarchical layers of latentvariables to construct predictors for high-dimensional input-output models.Training a deep learning architecture is computationally intensive, andefficient linear algebra libraries is the key for training and inference.Stochastic gradient descent (SGD) optimization and batch sampling are used tolearn from massive data sets.

2018-08-26T20:26:11Z

@machinelearning_tuts
@selfdrivecar
@autonomousvehicle
----------
Link : http://arxiv.org/abs/1808.08618v1

Geometrization of deep networks for the interpretability of deep learning systems

--Abstract
How to understand deep learning systems remains an open problem. In thispaper we propose that the answer may lie in the geometrization of deepnetworks. Geometrization is a bridge to connect physics, geometry, deep networkand quantum computation and this may result in a new scheme to reveal the ruleof the physical world. By comparing the geometry of image matching and deepnetworks, we show that geometrization of deep networks can be used tounderstand existing deep learning systems and it may also help to solve theinterpretability problem of deep learning systems.

2019-01-06T14:32:45Z

@machinelearning_tuts
@selfdrivecar
@autonomousvehicle
----------
Link : http://arxiv.org/abs/1901.02354v2

Distributed Stochastic Multi-Task Learning with Graph Regularization

--Abstract
We propose methods for distributed graph-based multi-task learning that arebased on weighted averaging of messages from other machines. Uniform averagingor diminishing stepsize in these methods would yield consensus (single task)learning. We show how simply skewing the averaging weights or controlling thestepsize allows learning different, but related, tasks on the differentmachines.

2018-02-11T22:23:34Z

@machinelearning_tuts
@selfdrivecar
@autonomousvehicle
----------
Link : http://arxiv.org/abs/1802.03830v1

15 Open Datasets For Deep Learning Enthusiasts https://www.analyticsindiamag.com/15-open-datasets-for-deep-learning-enthusiasts/