Workshop brief

Lots of buzzwords, lots of unicorns, but we will make it practical and lead you in your first steps to the magical place of data science, specifically, deep learning. We will talk a bit about the theory behind it, but mostly, we will demonstrate the variety of common techniques and usages. You will acquire the fundamental knowledge and tools to implement deep learning architecture by yourself.

What

5 sessions that are meant to change to help you learn the skill set of deep learning and develop your AI intuition.

When

We will meet 5 times, on Fridays between 9:00 to 14:00 (06.09, 13.09, 20.09, 27.09, 04.10)

Who

- Dr. Eyal Gruss - AI/Machine Learning/Deep Learning advisor and consultant
- Tamir Nave - Algorithms Expert as a Freelance: Deep learning, Computer Vision
- Assif Ziv - Senior data scientists at AT&T
- Maoz Tamir CTO - AI Factory
- Yechiel Amsalem - Senior data scientist at AT&T
- Ron Weiner VP R&D at Aivf and data scientist at ICV, Co-founder of Give & Tech

Who can join us?

The workshop is for anyone who has programming skills (preferably some knowledge of python), logic orientation, and an outstanding will to learn.
In the workshop, we will use python, tensorflow and keras.
This is a complex topic, you should work hard and be very focused during those weeks ^_^

Schedule
Session 1
AI Overview - Assif Ziv:
What differs AI from other kind of algorithms? What’s the relation between AI and Machine Learning? How did it all start and what is Deep Learning? In this lecture we will cover the buzz words, history and general notions around the topic of AI from a technical perspective.

Build the first Neural Network - Maoz Tamir
What is Neural Network and how to create one What is a biological neural network and how is it relevant to an artificial neural network. We’ll create a deep neural network with pure python and learn how to do a binary classification.

Data preprocessing pitfalls - Yechiel Amsalem
Data preprocessing in the wild It’s all All numbers Categories. The null problem Underflow overflow Scaling Feature selection Correlation Manually and using reduction technique called Principal Component Analysis. The Odd ones – outliers Understanding some key concepts which enable deep learning to be so incredible. “It’s your loss” customize loss function Control the network data feed Save and refit It’s always overtired Dropout Batch Normalization When GBM wins

Session 2
A shallow introduction to deep learning - Dr. Eyal Gruss
Basic terminology History and motivation Computer vision / image processing Generative adversarial networks (GANs) Natural language processing Multimodal methods combining image and text Video, audio, speech Game playing

Build the first Neural Network - Eyal Gruss
Neural Networks Keras Data preparation Training and optimizers Regularization Best practices MNIST and CIFAR10 datasets Image recognition

Deep Learning for computer vision - Eyal Gruss
Convolutions Convolutional neural networks, Preprocessing and data augmentation, Common architectures for image recognition, Overview of approaches for other computer vision tasks, Generative algorithms, Autoencoders (optional), Anomaly detection (optional)

Session 3

Introduction of rnn & lstm basics - Yechiel Amsalem
The sequential data source -What is a sequence -Sequence representation in 3d -Sequence in the real world -Sequence to sequence Squash your problems away LSTM network and sequence importance Why we need recurrent nets for time series data and why LSTMs increase our network’s memory.

NLP concepts - Yechiel Amsalem
NLP as a sequence problem Bag of words Embedding LDA Sentiment analysis – classifying text.

Complex RNN architectures- Yechiel Amsalem
Tensorflow library and Language Translator We’ll go over several translation methods and talk about how Google Translate is able to achieve state of the art performance.

Session 4
Image style transfer - Ron Weiner
How to Generate Art using giving style image and content image. How this process works and why deep learning does it so well. Exposure to less intuitive and more complex loss functions.

Image classification, Object Detection, object segmentation - Maoz Tamir
Using deep neural networks for image classification. The basic building blocks. Tips and tricks in image classification . Object detection basics ,classification with localization. Different types of Object detection networks – SSD , YOLO Object Segmentation.

Introduction to GAN - Tamir Nave
Deep convolutional GAN Generative Adversarial Networks. We’re going to use a Deep Convolutional GAN to generate images of pokemons. Architecture and implementation.

Session 5
Siamese network as small data solutions - Ron Weiner
How to Learn from Little Data One-shot classification for a small labeled image dataset. We’ll also go over the architecture of its inspiration.

Data science research - Yechiel Amsalem
Deep fake Non sequential data input NAS – neural architecture search Meta-Learning Transfer Learning

Open talk with the lecturers
Summary and what's next

This workshop was created by Give & Tech (Formally Tech4Charity) Non-Profit organization.
This is a non-profit workshop which donates all of the proceeds to Maslan, Rishon Loves Animals, Mechubarim Plus
Due to the charity characteristic of the workshop, there is a non-refund policy.
*** THE EVENT WILL BE HELD IN HEBREW***
*** THE TICKET THAT YOU CHOOSE REPRESENTS THE AMOUNT OF THE DONATION THAT YOU GIVE ***
*** ONE TICKET == ENTRANCE TO ALL OF THE 5 SESSIONS ***

If you've read until here we're sure it can interest you, so save the date - 06.09.19