|In this semester, we will cover two different topics: IoT and deep learning. The first part of this lecture will focus on wireless adhoc network technology that provide low energy and low latency lightweight communication for WSN (wireless sensor networks) and MANET (mobile adhoc networks). The second part of this class will focus on deep learning techniques of artificial intelligence. Recently, deep learning techniques are used not only for machine learning but also applied to other fields of information technology as well as to the other fields of engineering and science in general. We will discuss the basic concepts of deep learning such as CNN and RNN by studying the classical papers of machine learning and deep learning. Then, we move to more recent topics of deep learning such as reinforcement learning (RL) and generative adversarial networks (GAN) by reviewing the recent research papers in deep learning.|
1. Lecture Note 1 was updated on August 29th.
2. Lecture Note 2 was updated on September 11th.
3. Lecture Note 3 was updated on September 18th.
4. Lecture Note 4 was updated on October 9th.
5. Lecture Note 5 was updated on October 9th.
6. Lecture Note 6 was updated on October 16th.
7. Lecture Note 7 was updated on October 16th.
8. Lecture Note 8 was updated on November 1st.
9. Lecture Note 9 was updated on November 7th.
▣ Lecture slide
▣ Paper Presentation
- Probabilistic Recurrent State-Space Models
- The Kanerva Machine: A Generative Distributed Memory
- Unsupervised Predictive Memory in a Goal-Directed Agent
- FlowNet2.0 : Evolution of Optical Flow Estimation with Deep Networks
- Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
- SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
- 5G Virtualized Multi-access Edge Computing Platform for IoT Applications
- Breathing-Based Authentication on Resource-Constrained IoT Devices using Recurrent Neural Networks
- WE-Safe: A Self-Powered Wearable IoT Sensor Network for Safety Applications Based on LoRa
- Harmonium: Asymmetric, Bandstitched UWB for Fast, Accurate, and Robust Indoor Localization
- ODDS: Real-Time Object Detection using Depth Sensors on Embedded GPUs
- Enhancing Indoor Smartphone Location Acquisition using Floor Plans
- Dependable Visual Light-Based Indoor Localization with Automatic Anomaly Detection for Location-Based Service of Mobile Cyber-Physical Systems
- High Precision Infrastructure-free Mobile Device Tracking in Indoor Environments
- Ultra-Low Power Gaze Tracking for Virtual Reality
- Hybrid computing using a neural network with dynamic external memory
- Mastering the game of Go without human knowledge
- Mask R-CNN
Paper List : Paper List.docx
Convolutional Neural Network (12 papers)
Natural Language Processing / Recurrent Neural Network (12 papers)
Optimization / Training Techniques (10 papers)
Uderstanding / Generalization / Transfer (7 papers)
Recent papers (12 papers)
Classic papers (10 papers)
▣ Reading List