This course showcases the field of Deep Learning, concepts and algorithms in this branch of Machine Learning, and its implementation using modern neural network systems.
The labs in this course will use Python and Keras.
We will learn about the structure of neural networks, training techniques, CNN architectures, and we will analyze existing architectures and models.
Deep Learning Course – 3 Days Course
- Knowledge of / experience with some programming language.
- Background in Python will serve as advantage, but is not a mandatory requirement.
- Basic mathematical background in the fields of linear algebra, differential calculus.
- Participants are to bring a Laptop with them to the Lab. There is no need to install any software prior to the labs.
|Day #1||Day #2||Day #3||Location|
|May course:||Sunday 24.5||Monday 25.5||Tuesday 26.5||Tel-Aviv|
|July course:||Sunday 12.7||Monday 13.7||Tuesday 14.7||Tel-Aviv|
Course Description – Day 1:
- Introduction to Neural Networks
- Basics of Neural Network Programming – Binary classification, Logistic regression, cost function, gradient descent, derivatives, computation graph
- Shallow Neural Network – Neural networks with several layer, activation function, initialization
- Lab – Logistic regression with Neural Network mindset.
Course Description – Day 2:
- Deep Neural Networks – DNNs, parameter dimensions, why deep representations, forward and backward propagation, parameters vs. hyper parameters
- Convolutional Neural Networks – Motivation, padding, strides, volume, multiple filters, pooling layers, convnet example
- Detection Algorithms – classification with localization, sliding windows, fully connected to convolutional layer, bounding box prediction, IOU, NMS, anchor boxes
- Lab – Car detection with YOLO and Keras.
Course Description – Day 3:
- CNN Architectures – AlexNet, VGG, GoogLeNet, ResNet
- Deep Learning hardware and Software(TensorFlow/PyTorch)
- Optimization algorithms – Mini batch, exponentially weighted moving average, bias correction, gradient descent with momentum, RMSprop, ADAM
- Recurrent Neural Networks – RNNs, computational graph, backpropagation through time, image captioning, LSTM.
Lunch included at Carlton Hotel.
Enroll to receive price and course information.
I have read and agreed to the terms of service
Eliezer Peri St 10 (Carlton Hotel), Tel Aviv, Israel