Deep Learning for Computer Vision 2. Go deeper
The course aims to present basics knowledge of modern approaches which are used for solving computer vision problems: from descriptions of solutions based on deep convolution networks with hacks and practical examples.
Theory part (lectures):
- Lecture I: Advanced overview of topologies. Structure, accuracy, size, inference time.
- Lecture II : Tips and tricks for finetunning neural networks. Light weight neural networks.
- Lecture III : Light weight neural networks (part 2). Ways to reduce model’s size/speed saving accuracy level.
Python, NN framework: pytorch
Вимоги до попередніх знань
Basic linear algebra, proficiency in Python, machine learning basics (understanding of different types of learning (supervised, unsupervised, reinforcement learning), classification, regression problems, generalization error, overfitting, train/test datasets split). Optional, but desirable: neural network (NN) basics, feed forward NN, different activation functions, backpropagation.
I am a Deep Learning Researcher at Ring Labs Kyiv with a focus on Computer Vision. I have worked on solving object detection and object classification problems. Also, I am last year Master’s student in Statistics at Mechanical and Mathematical Faculty at Taras Shevchenko National University of Kyiv.
Field of interests: Deep Learning, Computer Vision and Machine Learning