Israel Goytom

Beep boop, building payment infrastrucures for Africa.

I am a Co-founder and CTO at Chapa. Where I spend most of my time attending meetings, coding, reviewing codes and studying human brain. Previously, I was working in Yoshua Bengio's lab MILA on problems related to Humanitarian AI with post doc Kris Sankaran.

Email  /  Google Scholar  /  Github  /  Plane project lists

profile photo
Research

I'm interested in machine learning, computer vision, data mining and deep learning in particle physics. I’m most interested in physics real world problems and machine learning especially applying deep learning algorithms to solve numerous physics problems. I am also interested in social media data mining for social good projects. I sporadically share my opinions to my Twitter and many of my projects are available on my Github.

HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion
Michel Deudon* , Alfredo Kalaitzis*, Md Rifat Arefin, Israel Goytom, Kris Sankaran, Zhichao Lin, Vincent Michalski, Samira E. Kahou, Julien Cornebise, Yoshua Bengio
Submitted to ICLR, 2020
code / amazing blog

We introduce HighRes-Net, a recursive neural network for MFSR, as well as shiftNet-Lanczos, a neural network for image registration. We discuss our cooperative learning setting and compare our results to state-of-the-art Single-Image Super-Resolution (SISR) baselines on the European Space Agency's Kelvin competition

Forecasting Extremes in Time Series for Climate Change
Israel Goytom, Kris Sankaran
IWCI, 2019
code

We propose an LSTM model with Gumbel-distributed errors, as one way to combine classical theory of extreme values with modern deep learning.

Nanoscale Microscopy Images Colourization Using Neural Networks
Israel Goytom, Qin Wang, Kris Sankaran, Dongdong Lin
Submitted, 2019

code

We introduce two artificial neural networks for grey microscopy image colorization: A convolutional neural network (CNN) with a pre-trained Inception ResNetV2 model for feature extraction. A Neural Style Transfer convolutional neural network (NST-CNN), which can colorize grey microscopy images with semantic information learned from a user-provided color image at inference time.

A Machine learning approach to detect and classify 3D two-photon polymerization Microstructures using optical microscopy images
Israel Goytom, Gu Yinwei
CSEIT, 2018

poster

For 3D microstructures fabricated by two-photon polymerization, a practical approach of machine learning for detection and classification in their optical microscopic images is state and demonstrated in this paper.

Patents
Type 3D Axis Microscope (China Patent No. ZL 2018 2 0805917.2)

cs188 A device for detecting similar proportions between micro-structures on PVC (China Patent No. CN207036728U)

Cloned from here