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.
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 ^_^
Each workshop day is built from 3 training sessions.
Sessions 1 and 2 also includes a 30 minutes hands-on practice, don’t forget to bring your laptop!
Practice makes perfect – at the each workshop day we will reveal our weekly challenge.
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.
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 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
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
Training and optimizers
MNIST and CIFAR10 datasets
Convolutional neural networks
Preprocessing and data augmentation
Common architectures for image recognition
Overview of approaches for other computer vision tasks
Anomaly detection (optional)
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 as a sequence problem
Bag of words
Sentiment analysis – classifying text
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.
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.
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
Deep convolutional GAN
Generative Adversarial Networks.
We’re going to use a Deep Convolutional GAN to generate images of pokemons. Architecture and implementation.
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 .
Non sequential data input
NAS – neural architecture search
Summarize & what’s next