Wharton's Entrepreneurship Specialization covers the conception, design, organization, and management of new enterprises. This five-course series is designed to take you from opportunity identification through launch, growth, financing and profitability. With guidance from Wharton's top professors, along with insights from current Wharton start-up founders and financiers, you'll develop an entrepreneurial mindset and hone the skills you need to develop a new enterprise with potential for growth and funding, or to identify and pursue opportunities for growth within an existing organization.
https://www.coursera.org/specializations/wharton-entrepreneurship

Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better supervised learning algorithms. However, in stark contrast to young animals (including humans), training such networks requires enormous numbers of labeled examples, leading to the belief that animals must rely instead mainly on unsupervised learning. Here we argue that most animal behavior is not the result of clever learning algorithms—supervised or unsupervised—but is encoded in the genome. Specifically, animals are born with highly structured brain connectivity, which enables them to learn very rapidly. Because the wiring diagram is far too complex to be specified explicitly in the genome, it must be compressed through a “genomic bottleneck”. The genomic bottleneck suggests a path toward ANNs capable of rapid learning.
https://www.nature.com/articles/s41467-019-11786-6

An insightful website which contains a history of cybernetic animals and early robots
https://cyberneticzoo.com

Discussions about several issues relevant to trial-and-error learning (Reinforcement Learning), including prediction,
expectation, and what this paper called the basic credit-assignment problem for complex reinforcement
learning systems: How do you distribute credit for success among the many
decisions that may have been involved in producing it? (Published 1961)

A Brief introduction to Statistical Learning theory

Computational Learning Theory versus Statistical Learning Theory
While both frameworks use similar mathematical analysis, the primary difference between CoLT and SLT are their objectives. CoLT focuses on studying “learnability,” or what functions/features are necessary to make a given task learnable for an algorithm. Whereas SLT is primarily focused on studying and improving the accuracy of existing training programs.
https://deepai.org/machine-learning-glossary-and-terms/computational-learning-theory

A brief introduction to stochastic approximation theory

Brains, Minds, and Machines summer course
https://www.youtube.com/watch?v=_svW8NV1A6k&list=PLUl4u3cNGP61RTZrT3MIAikp2G5EEvTjf&index=1

A 20 steps guide to write a book

🔻پنجمین دورهمی مدرسه جهانی هوش مصنوعی در رشت
🔺School of AI

📘موضوع این جلسه: عصب شناسی محاسباتی و رابطه آن با هوش مصنوعی
🗓دوشنبه 11 شهریور 1398
🕐ساعت 16:30 الی 19:00
🏢 رشت، میدان انتظام (پل رازی)، پارک علم و فناوری گیلان

*جهت ثبت نام به لینک زیر مراجعه کنید:
▪️https://evnd.co/WtokW

برای کسب اطلاعات بیشتر درباره ی این مدرسه، به کانال زیر مراجعه کنید:
🏢 @schoolofairasht

✅ @Brainandcognition_GU

What is “ML Ops”? Best Practices for DevOps for ML
https://www.itsalways10.com/what-is-ml-ops-best-practices-for-devops-for-ml/

A Shared Vision for Machine Learning in Neuroscience
https://www.jneurosci.org/content/jneuro/38/7/1601.full.pdf

Deep Neural Networks in Computational Neuroscience
https://www.biorxiv.org/content/biorxiv/early/2017/05/04/133504.full.pdf

Fast-Bert

This library will help you build and deploy BERT based models within minutes:

Fast-Bert is the deep learning library that allows developers and data scientists to train and deploy BERT and XLNet based models for natural language processing tasks beginning with Text Classification.

The work on FastBert is built on solid foundations provided by the excellent Hugging Face BERT PyTorch library and is inspired by fast.ai and strives to make the cutting edge deep learning technologies accessible for the vast community of machine learning practitioners.

With FastBert, you will be able to:

Train (more precisely fine-tune) BERT, RoBERTa and XLNet text classification models on your custom dataset.

Tune model hyper-parameters such as epochs, learning rate, batch size, optimiser schedule and more.

Save and deploy trained model for inference (including on AWS Sagemaker).

Fast-Bert will support both multi-class and multi-label text classification for the following and in due course, it will support other NLU tasks such as Named Entity Recognition, Question Answering and Custom Corpus fine-tuning.

Blog post: https://medium.com/huggingface/introducing-fastbert-a-simple-deep-learning-library-for-bert-models-89ff763ad384

Code: https://github.com/kaushaltrivedi/fast-bert

#language_model #BERT