Grid search vs randomized search?
💡 What are the pros and cons of grid search? Pros: • Grid search is great when you need to fine-tune hyperparameters over a small search space automatically. • For example, if you have 100 different datasets that you expect to be similar (e.g. solving the same problem repeatedly with different populations), you can use grid search to automatically fine-tune the hyperparameters for each model. Cons: • Grid search is computationally expensive and inefficient, often searching over parameter space that has very little chance of being useful, resulting it being extremely slow. It's especially slow if you need to search a large space since it's complexity increases exponentially as more hyperparameters are optimized.
💡 What are the pros and cons of randomized search? Pros: • Randomized search does a good job finding near-optimal hyperparameters over a very large search space relatively quickly and doesn't suffer from the same exponential scaling problem as grid search. Cons: • Randomized search does not fine-tune the results as much as grid search does since it typically does not test every possible combination of parameters.
#datascience
👉 Free training -> http://bit.ly/dsdj-webinar


❇️ @AI_Python_EN

Machine Learning w.r.t meditation routine.
Machine before meditation = underfitting
Machine after meditation = optimal fitting
Planning of meditation = overfitting
#datascience

❇️ @AI_Python_EN

Trying the online demo of GPT-2 based text generator.
https://transformer.huggingface.co/doc/gpt2-large

#deeperlearning #machinelearning

❇️ @AI_Python_EN

Four keys to #machinelearning on the edge
Machine learning is hard. Moving your ML model to embedded devices can be even harder.


https://bit.ly/2KjUEh6

❇️ @AI_Python_EN

AI IN 2018: A YEAR IN REVIEW

#artificialintelligence #AI #MachineLearning

https://medium.com/@AINowInstitute/ai-in-2018-a-year-in-review-8b161ead2b4e

❇️ @AI_Python_EN

25 Best Free #Dataset s for Machine Learning

https://www.edureka.co/blog/25-best-free-datasets-machine-learning/

❇️ @AI_Python_EN

MIT Technology Review:
A #NeuralNet solves the three-body problem 100 million times faster

#MachineLearning #mathematics

🔰 NeuralNet

🔰 Paper

❇️ @AI_Python_EN

Brown University’s Data Science Initiative (DSI) seeks applicants for a lecturer, senior lecturer, or distinguished senior lecturer. The initial appointment is for a 3-year period (renewable with potential for promotion and longer-term contracts). The position involves teaching four courses

per year and providing administrative or advising support for student programs. We seek candidates who will contribute to our overall intellectual culture. Lecturers with substantial research participation and supporting funds may be eligible for periodic course release. Please see our Interfolio posting for more details and to apply. 
https://apply.interfolio.com/70943

❇️ @AI_Python_EN

3 Ways to Encode Categorical Variables for Deep Learning

https://machinelearningmastery.com/how-to-prepare-categorical-data-for-deep-learning-in-python/

❇️ @AI_Python_EN

Deep Learning in mobile and wireless networking:
https://arxiv.org/pdf/1803.04311.pdf
ML in telecom:
https://jisajournal.springeropen.com/articles/10.1186/s13174-018-0087-2

❇️ @AI_Python_EN

How to process images in Python

https://morioh.com/p/f469f74855f6

#Python

❇️ @AI_Python_EN

Evolving Neural Networks
A tutorial on evolutionary algorithms

https://towardsdatascience.com/evolving-neural-networks-b24517bb3701

#NeuralNetworks #ReinforcementLearning

❇️ @AI_Python_EN

Release: CCNet is our new tool for extracting high-quality and large-scale monolingual corpora from CommonCraw in more than a hundred languages.
Paper:
https://arxiv.org/abs/1911.00359
Tool:
https://github.com/facebookresearch/cc_net

❇️ @AI_Python_EN

Who is winning the #AI race : China 🇨🇳, Europe🇪🇺 or US 🇺🇸?

Interesting 106 page report from Aug 2019 by "Center for data innovation"
I personally believe that innovation will come from a true borderless exchange of technology & talent in democratic and responsible societies.

#artificialintelligence #machinelearning

❇️ @AI_Python_EN

Adobe Research is offering audio research internships in San Francisco and Seattle in 2020. We are looking for PhD students who are excited about pushing the state of the art in the field and having a 

Please use “Audio Research Internship” as the title of your application email.

...more

❇️ @AI_Python_EN

The Interactive Media Group at Microsoft Research, Redmond has several openings for research internships. For over 20 years, our interns have been conducting influential research published in top-tier venues such as SIGGRAPH, CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, JASA. We are looking for motivated students in various topics including, but not limited to,

computer vision, machine learning, object detection and tracking,scene understanding,3D reconstruction, computational photography, learning from simulation, mixed/augmented reality ,unsupervised representation learning , 
multimodal learning for video understanding, physically-based sound synthesis and propagation, deep learning for vision, graphics, and acoustics

For details on our research group and projects, please see:

http://research.microsoft.com/en-us/groups/graphics/

We are located at Microsoft headquarters in Redmond, near Seattle, Washington. We strive to make our internships fun, productive, and profitable (salary, and transportation, etc.).

HOW TO APPLY:

If interested, please apply here:

https://careers.microsoft.com/us/en/job/736933/Research-Intern-Computer-Vision-Machine-Learning-Graphics-Sound-Propagation-within-IMG

❇️ @AI_Python_EN

We are looking for summer interns at Nokia Bell Labs to work on machine learning research projects in summer 2020. Job details are as follows: 

Human Augmented Sensing Summer Student

MSc or PhD students in CS, computational and applied math, OR, EE, or related fields (eg, computational physics and chemistry).

Have a deep understanding of machine learning/IP networking and expertise in related areas such as machine learning tools and applications, software defined networking and algorithmic aspects of networking.

Proven track record of research contributions and publications in leading and internationally recognized conferences and journals.

Student Criteria:

Overall GPA of 3.0/4.0 or above.

Must be enrolled as a full-time student.

Work Authorization:  

U.S. Citizen or Permanent Resident preferred.  Will accept students on F-1 Visa dependent upon program requirements or may consider sponsoring short-term J1 Visa PhD students dependent upon program requirements.

To apply, please go to

https://aluperf.referrals.selectminds.com/jobs/bell-labs-intern-augmented-human-sensing-36720

❇️ @AI_Python_EN

Conversation with Gilbert Strang, a professor of mathematics at MIT & an inspiring teacher of linear algebra to millions of students around the world through MIT OpenCourseWare.

https://www.youtube.com/watch?v=lEZPfmGCEk0

❇️ @AI_Python_EN

Another nice visual guide by Jay Alammar about how you can use BERT to do text classification. In particular, he’s using DistilBERT to create sentence embeddings which is then used as an input for logistic regression. Code is also provided! Check it out! #deeplearning #machinelearning #NLP
📝 Article:
https://jalammar.github.io/a-visual-guide-to-using-bert-for-the-first-time/

❇️ @AI_Python_EN

Machine Learning From Scratch

https://github.com/eriklindernoren/ML-From-Scratch
#ArtificialIntelligence #DeepLearning #MachineLearning

❇️ @AI_Python_EN