WhoAmI

foto

I started the journey with the study Mechatronics at The Hague Applied Sciences (focus on machine learning, robotics and computer vision). After my graduation, I worked part-time at a company, and working on my pre-master, at the TU Delft for the master computer engineering (started in February 2019). Hopefully, I will finish my master before September 2020.

Currently

I am working on my thesis in Spiking Neural Networks see following link blog post

Master topics

This is a list of master topics that I followed:

  • Network Security (Parts of Advance Network Security and crypto)
  • Deep Learning, Computer Vision
  • CPU design: caches, core, ALU (like a 2-cycle multiplier)
  • GPU, FPGA, Multi-data instructions
  • Operating systems
  • ADHOC networks focus on mesh-networks
  • Web data management
  • Entrepreneurship, business plan

Software skills

Advance Experience Beginner
C Makefiles Rust
C++ Linkerscripts PHP
Python Matlab
Bash
Angular (>V2)
Node.js
Databases:
  • MongoDB
  • SQL
VHDL
Verilog

Artificial Intelligence

The main focus of my career is the field of Artificial Intelligence (Machine Learning, Deep Learning, Spiking Neural Networks). I believe that the first thing that needs to be done is using non Artificial Intelligence algorithm. The field is quite large with many focus points, therefor I made a small list with AI methods that I have been working with.

Machine learning
MLP
SVM
Cross-validation
n-fold rule
Descision trees
Adaboost, Bagging, Stumping
Model reduction
PCA, SOM, many more
Viola and Jones
Learning methods: Momentum, Rprop, Adams
Activation functions
Novelty detection
Heat-maps and other data validation techniques
Regression
Small evolutionary algorithm with fitness function
Time-serie dataset
Normalization techniques

The following list is for deep learning.

Deep learning
RESNet and variants
VGG and variants
Inception and variants
Attention learning
GANs
LSTMs
BabyRNN
C++ implementation of a CNN
Framework Keras (see paper-blog for source code)

The following list is for spiking neural networks.

Spiking Neural Networks
digital ANN to analog SNN
Rate encoding
Threshold encoding
Leaky-integrate and fire
LSM (just touched)