Mike Schachter, Developer in Castro Valley, CA, United States
Mike is available for hire
Hire Mike

Mike Schachter

Verified Expert  in Engineering

Neuroscience Developer

Location
Castro Valley, CA, United States
Toptal Member Since
July 14, 2022

Mike has over 20 years of experience in machine learning, data science, and computational biology. His expertise includes signal and image processing, working with unstructured data such as images, video, audio, and text, and he is proficient in time series analysis. Extending from leveraging cloud platforms such as GCP and AWS to writing Python, R, C++, and Java code, Mike's technical experience resulted in significant contributions to the field of neuroscience.

PythonMachine LearningWeb DevelopmentTime Series AnalysisPyTorchOpenCVTensorFlowRDeep LearningComputer VisionAmazon Web Services (AWS)Big DataDistributed SystemsProbabilistic Graphical ModelsTime SeriesBioinformaticsComputational Biology

Portfolio

Parker Institute for Cancer Immunotherapy
Python, R, Bioinformatics, Deep Learning, Computer Vision
Google
R, Python, BERT, Big Data, Data Science, Deep Learning
Inscopix
Python, MATLAB, C++, OpenCV, Deep Learning, Computer Vision

Experience

Python - 12 yearsNeuroscience - 12 yearsWeb Development - 10 yearsMachine Learning - 10 yearsTime Series Analysis - 6 yearsData Science - 6 yearsOpenCV - 3 yearsBioinformatics - 1 year

Availability

Part-time

Preferred Environment

Python, PyTorch, TensorFlow, R, C++, OpenCV, Google Cloud Platform (GCP), Time Series Analysis, Amazon Web Services (AWS)

The most amazing...

...thing I've worked on is the molecular analysis of brain tumors to identify therapeutic targets and fight this devastating disease.

Work Experience

Postdoctoral Fellow in Data Science

2021 - PRESENT
Parker Institute for Cancer Immunotherapy
  • Performed the analysis of transcriptomic data obtained from hundreds of subjects and thousands of single cells. Currently focused on analyzing tumor-immune microenvironment in gliomas.
  • Implemented spatial biology technologies by analyzing multiplex images of tumors.
  • Worked with a team of academic collaborators to test hypotheses and aggregate clinical and molecular data.
Technologies: Python, R, Bioinformatics, Deep Learning, Computer Vision

Data Scientist

2019 - 2021
Google
  • Derived insights related to the Google Assistant search queries by performing unsupervised analysis using the BERT and clustering models.
  • Oversaw establishing and maintaining the requirements of quantitative and qualitative metrics of Google Assistant for the release of Chromecast for Google TV.
  • Worked with various software development teams for Google Assistant on Android TV to develop metrics for evaluating search quality.
Technologies: R, Python, BERT, Big Data, Data Science, Deep Learning

Data Scientist

2016 - 2019
Inscopix
  • Refined and automated video processing algorithms and pipelines using machine learning.
  • Quantified brain activity in awake, behaving animals using time series analysis.
  • Participated in collaborative efforts to develop neurodegenerative disease assays.
Technologies: Python, MATLAB, C++, OpenCV, Deep Learning, Computer Vision

Doctoral Researcher

2010 - 2016
University of California, Berkeley
  • Extracted complex acoustic features from audio signals using DSP and time-frequency analysis.
  • Applied multivariate time series analysis to brain signals to extract their meaning, related to work in brain-machine interfaces.
  • Taught classes in Machine Learning in Python and Statistics in R to graduate students.
  • Researched deep networks and implemented basic neural network algorithms.
Technologies: Amazon Web Services (AWS), Distributed Systems, Python, MATLAB, Deep Learning, Audio, Signal Analysis, Statistics, Probability Theory, Probabilistic Graphical Models, Information Theory, Time Series Analysis, Time Series, Digital Signal Processing, Multivariate Statistical Modeling, R

Study of Neuropsychiatric Diseases Using Machine Learning

https://www.frontiersin.org/articles/10.3389/fnins.2019.00176/full
I worked with researchers at Janssen to quantify the relationship between chronic stress and spatial encoding in groups of neurons. I developed algorithms to decode the position of mice on a linear track based on their neural activity and quantified the extent to which chronic stress altered spatial encoding.

Acoustic Features Decoding from Brain Activity

https://escholarship.org/uc/item/1mp6c5mx
In this project, I analyzed the relationship between the sounds an animal hears and their distributed representation in the brain. The work leverages machine learning, signal processing, and time series analysis to uncover what acoustic features of sounds are represented by collections of neurons in the zebra finch auditory cortex.

Single Neuron Activity Simulation

https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000899
After undergraduate studies, I worked in a neuroscience lab as part of a team that developed computational models of the electrical activity of single neurons that detect motion. This project involved simulations of highly nonlinear electrical circuits, a deep understanding of how ion channels generate electrical activity in brain cells, and a sense of how the retina processes images.
2010 - 2016

PhD in Neuroscience

University of California, Berkeley - Berkeley, CA

2002 - 2005

Bachelor's Degree in Mathematics

Temple University - Philadelphia, PA

AUGUST 2021 - PRESENT

Applied Bioinformatics

University of California San Diego

Libraries/APIs

Scikit-learn, PyTorch, TensorFlow, OpenCV

Tools

MATLAB

Languages

Python, R, C++

Industry Expertise

Bioinformatics

Paradigms

Data Science

Platforms

Google Cloud Platform (GCP), Amazon Web Services (AWS)

Other

Neuroscience, Time Series Analysis, Machine Learning, Web Development, Computational Biology, Mathematics, Computer Science, BERT, Big Data, Deep Learning, Computer Vision, Distributed Systems, Audio, Signal Analysis, Statistics, Probability Theory, Probabilistic Graphical Models, Information Theory, Time Series, Digital Signal Processing, Multivariate Statistical Modeling

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring