“I have worked with Maciej for the last 3 years on a few projects. Maciej was my manager and coach in the big data sensor/IoT streaming platform. Under his leadership, we have successfully built a near real-time streaming platform with high reliability and availability. Maciej is exceptionally intelligent, creative, dynamic, organized, enthusiatic about technology and science. The first project I have worked with Maciej is on 3D Medical Imaging/Visualization product. Maciej shows his expertise in data modeling, deep brain visualization, and proficient software skills. He often came up with great solutions for difficult problems over night and highly respected by the team and research peers. Most recently, I had the privilege working on the big data platform under Maciej's guidance. I am impressed by his deep understanding about machine learning, mathematical modeling, and broad expereiences in big data, IoT, and cloud computing. Working with Maciej is one of my best experiences.”
About
As a Full Stack Deep Learning and Big Data expert, I specialize in translating complex…
Activity
-
𝗔 𝗚𝗿𝗲𝗮𝘁 𝗕𝗼𝗼𝗸 𝗮𝗯𝗼𝘂𝘁 𝗧𝗶𝗺𝗲 𝗦𝗲𝗿𝗶𝗲𝘀 𝗙𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴! 📈 Time series are prevalent in science, business and finance, making…
𝗔 𝗚𝗿𝗲𝗮𝘁 𝗕𝗼𝗼𝗸 𝗮𝗯𝗼𝘂𝘁 𝗧𝗶𝗺𝗲 𝗦𝗲𝗿𝗶𝗲𝘀 𝗙𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴! 📈 Time series are prevalent in science, business and finance, making…
Liked by Maciej Lazarewicz
-
With today’s launch of our Llama 3.1 collection of models we’re making history with the release of the largest and most capable open source AI model…
With today’s launch of our Llama 3.1 collection of models we’re making history with the release of the largest and most capable open source AI model…
Liked by Maciej Lazarewicz
-
𝐒𝐩𝐢𝐧𝐐𝐮𝐚𝐧𝐭: 𝐋𝐋𝐌 𝐐𝐮𝐚𝐧𝐭𝐢𝐳𝐚𝐭𝐢𝐨𝐧 𝐰𝐢𝐭𝐡 𝐋𝐞𝐚𝐫𝐧𝐞𝐝 𝐑𝐨𝐭𝐚𝐭𝐢𝐨𝐧𝐬 Post-training quantization (PTQ) techniques greatly…
𝐒𝐩𝐢𝐧𝐐𝐮𝐚𝐧𝐭: 𝐋𝐋𝐌 𝐐𝐮𝐚𝐧𝐭𝐢𝐳𝐚𝐭𝐢𝐨𝐧 𝐰𝐢𝐭𝐡 𝐋𝐞𝐚𝐫𝐧𝐞𝐝 𝐑𝐨𝐭𝐚𝐭𝐢𝐨𝐧𝐬 Post-training quantization (PTQ) techniques greatly…
Liked by Maciej Lazarewicz
Experience
Education
-
-
-
-
-
* STATS 202 DATA MINING AND ANALYSIS (Machine Learning)
* STATS 290 PARADIGMS COMPUTING WITH DATA (Advanced R)
project: https://github.com/mlazarew/ropenfda
* STATS 315B MODERN APPL STAT: DATA MINING (Advanced Machine Learning) -
-
Activities and Societies: Competing on Business Analytics and Big Data, Negotiation and Leadership
-
-
-
-
-
-
Working on the PhD individual program under supervision of prof Ryszard Tadeusiewicz.
-
-
Licenses & Certifications
-
-
-
-
-
-
-
Data Mining with Weka, More Data Mining with Weka
The University of Waikato, Hamilton NZ
Issued -
-
Developing and Validating Software for the Medical Device Industry
Association for the Advancement of Medical Instrumentation
Issued -
Effective Application of Agile Practices in the Development of Medical Device Software
Association for the Advancement of Medical Instrumentation
Issued -
Amazon Elastic MapReduce 3-Day Developer Course
Think Big Analytics
Issued -
Certified Scrum Product Owner
Scrum Alliance, Inc.
Issued ExpiresCredential ID 000192976 -
C# course
Intertech
-
-
Data Analysis in R, the data.table Way
DataCamp
Credential ID 9b370cf79180f380e9a1bc03844c0b2b97835bbc -
Data Analysis in R, the data.table Way
DataCamp
Credential ID 9b370cf79180f380e9a1bc03844c0b2b97835bbc -
-
Volunteer Experience
-
Machine Learning Advisor
Spark Technology Center
- 11 months
Science and Technology
Participating in the Spark.tc Advisory Council with a focus on improving support for machine learning.
-
Chair of AI Session at Science and Technology Annual Conference
Medtronic
- 3 years
Science and Technology
-
-
-
-
PMI Data and Analytics Insight Team Advisor
Project Management Institute
- Present 3 years
Education
The PMI Data and Analytics Insight Team Supports PMI’s commitment to utilizing data to make informed decisions. The Data and Analytics Insight Team provides feedback to staff regarding data management, quality, analytics, and governance. The work helps to create a more data driven organization which can make quicker, better decisions.
Publications
-
Ih tunes theta/gamma oscillations and cross-frequency coupling in an in silico CA3 model.
PLoS One
Ih channels are uniquely positioned to act as neuromodulatory control points for tuning hippocampal theta (4-12 Hz) and gamma (> 25 Hz) oscillations, oscillations which are thought to have importance for organization of information flow. Ih contributes to neuronal membrane resonance and resting membrane potential, and is modulated by second messengers. We investigated Ih oscillatory control using a multiscale computer model of hippocampal CA3, where each cell class (pyramidal, basket, and…
Ih channels are uniquely positioned to act as neuromodulatory control points for tuning hippocampal theta (4-12 Hz) and gamma (> 25 Hz) oscillations, oscillations which are thought to have importance for organization of information flow. Ih contributes to neuronal membrane resonance and resting membrane potential, and is modulated by second messengers. We investigated Ih oscillatory control using a multiscale computer model of hippocampal CA3, where each cell class (pyramidal, basket, and oriens-lacunosum moleculare cells), contained type-appropriate isoforms of Ih. Our model demonstrated that modulation of pyramidal and basket Ih allows tuning theta and gamma oscillation frequency and amplitude. Pyramidal Ih also controlled cross-frequency coupling (CFC) and allowed shifting gamma generation towards particular phases of the theta cycle, effected via Ih's ability to set pyramidal excitability. Our model predicts that in vivo neuromodulatory control of Ih allows exibly controlling CFC and the timing of gamma discharges at particular theta phases.
Other authorsSee publication -
A translational platform for prototyping closed-loop neuromodulation systems
Frontiers in Neural Circuits
While modulating neural activity through stimulation is an effective treatment for neurological diseases such as Parkinson’s disease and essential tremor, an opportunity for improving neuromodulation therapy remains in automatically adjusting therapy to continuously optimize patient outcomes. Practical issues associated with achieving this include the paucity of human data related to disease states, poorly validated estimators of patient state, and unknown dynamic mappings of optimal…
While modulating neural activity through stimulation is an effective treatment for neurological diseases such as Parkinson’s disease and essential tremor, an opportunity for improving neuromodulation therapy remains in automatically adjusting therapy to continuously optimize patient outcomes. Practical issues associated with achieving this include the paucity of human data related to disease states, poorly validated estimators of patient state, and unknown dynamic mappings of optimal stimulation parameters based on estimated states. To overcome these challenges, we present an investigational platform including: an implanted sensing and stimulation device to collect data and run automated closed-loop algorithms; an external tool to prototype classifier and control-policy algorithms; and real-time telemetry to update the implanted device firmware and monitor its state. The prototyping system was demonstrated in a chronic large animal model studying hippocampal dynamics. We used the platform to find biomarkers of the observed states and transfer functions of different stimulation amplitudes. Data showed that moderate levels of stimulation suppress hippocampal beta activity, while high levels of stimulation produce seizure-like after-discharge activity. The biomarker and transfer function observations were mapped into classifier and control-policy algorithms, which were downloaded to the implanted device to continuously titrate stimulation amplitude for the desired network effect. The platform is designed to be a flexible prototyping tool and could be used to develop improved mechanistic models and automated closed-loop systems for a variety of neurological disorders.
Other authorsSee publication -
Advancing neuromodulation using a dynamic control framework.
Engineering in Medicine and Biology Society, the IEEE
The current state of neuromodulation can be cast in a classical dynamic control framework such that the nervous system is the classical "plant", the neural stimulator is the controller, tools to collect clinical data are the sensors, and the physician's judgment is the state estimator. This framework characterizes the types of opportunities available to advance neuromodulation. In particular, technology can potentially address two dominant factors limiting the performance of the control system:…
The current state of neuromodulation can be cast in a classical dynamic control framework such that the nervous system is the classical "plant", the neural stimulator is the controller, tools to collect clinical data are the sensors, and the physician's judgment is the state estimator. This framework characterizes the types of opportunities available to advance neuromodulation. In particular, technology can potentially address two dominant factors limiting the performance of the control system: "observability," the ability to observe the state of the system from output measurements, and "controllability," the ability to drive the system to a desired state using control actuation. Improving sensors and actuation methods are necessary to address these factors. Equally important is improving state estimation by understanding the neural processes underlying diseases. Development of enabling technology to utilize control theory principles facilitates investigations into improving intervention as well as research into the dynamic properties of the nervous system and mechanisms of action of therapies. In this paper, we provide an overview of the control system framework for neuromodulation, its practical challenges, and investigational devices applying this framework for limited applications. To help motivate future efforts, we describe our chronically implantable, low-power neural stimulation system, which integrates sensing, actuation, and state estimation. This research system has been implanted and used in an ovine to address novel research questions.
Other authorsSee publication -
Ketamine disrupts theta modulation of gamma in a computer model of hippocampus
Journal of Neuroscience
Abnormalities in oscillations have been suggested to play a role in schizophrenia. We studied theta-modulated gamma oscillations in a computer model of hippocampal CA3 in vivo with and without simulated application of ketamine, an NMDA receptor antagonist and psychotomimetic. Networks of 1200 multi-compartment neurons (pyramidal, basket and oriens-lacunosum moleculare, OLM, cells) generated theta and gamma oscillations from intrinsic network dynamics: basket cells primarily generated gamma and…
Abnormalities in oscillations have been suggested to play a role in schizophrenia. We studied theta-modulated gamma oscillations in a computer model of hippocampal CA3 in vivo with and without simulated application of ketamine, an NMDA receptor antagonist and psychotomimetic. Networks of 1200 multi-compartment neurons (pyramidal, basket and oriens-lacunosum moleculare, OLM, cells) generated theta and gamma oscillations from intrinsic network dynamics: basket cells primarily generated gamma and amplified theta, while OLM cells strongly contributed to theta. Extrinsic medial septal inputs paced theta and amplified both theta and gamma oscillations. Exploration of NMDA receptor reduction across all location combinations demonstrated that the experimentally-observed ketamine effect occurred only with isolated reduction of NMDA receptors on OLMs. In the ketamine simulations, lower OLM activity reduced theta power and disinhibited pyramidal cells, resulting in increased basket cell activation and gamma power. Our simulations predict:
• ketamine increases firing rates; • oscillations can be generated by intrinsic hippocampal circuits; • medial septum inputs pace and augment oscillations; • pyramidal cells lead basket cells at the gamma peak but lag at trough; • basket cells amplify theta rhythms; • ketamine alters oscillations due to primary blockade at OLM NMDA receptors; • ketamine alters phase relationships of cell firing; • ketamine reduces network responsivity to the environment • ketamine effect could be reversed by providing a continuous inward current to OLM cells.
We suggest that this last prediction has implications for a possible novel treatment for cognitive deficits of schizophrenia by targeting OLM cells.Other authors -
-
Ketamine modulates theta and gamma oscillations.
Journal of Cognitive Neuroscience/MIT Press
Ketamine, an N-methyl-D-aspartate (NMDA) receptor glutamatergic antagonist, has been studied as a model of schizophrenia when applied in subanesthetic doses. In EEG studies, ketamine affects sensory gating and alters the oscillatory characteristics of neuronal signals in a complex manner. We investigated the effects of ketamine on in vivo recordings from the CA3 region of mouse hippocampus referenced to the ipsilateral frontal sinus using a paired-click auditory gating paradigm. One issue of…
Ketamine, an N-methyl-D-aspartate (NMDA) receptor glutamatergic antagonist, has been studied as a model of schizophrenia when applied in subanesthetic doses. In EEG studies, ketamine affects sensory gating and alters the oscillatory characteristics of neuronal signals in a complex manner. We investigated the effects of ketamine on in vivo recordings from the CA3 region of mouse hippocampus referenced to the ipsilateral frontal sinus using a paired-click auditory gating paradigm. One issue of particular interest was elucidating the effect of ketamine on background network activity, poststimulus evoked and induced activity. We find that ketamine attenuates the theta frequency band in both background activity and in poststimulus evoked activity. Ketamine also disrupts a late, poststimulus theta power reduction seen in control recordings. In the gamma frequency range, ketamine enhances both background and evoked power, but decreases relative induced power. These findings support a role for NMDA receptors in mediating the balance between theta and gamma responses to sensory stimuli, with possible implications for dysfunction in schizophrenia.
Other authorsSee publication -
NMDA/AMPA ratio impacts state transitions and entrainment to oscillations in a computational model of the nucleus accumbens medium spiny projection neuron
The Journal of Neuroscience/SFN
We describe a computational model of the principal cell in the nucleus accumbens (NAcb), the medium spiny projection (MSP) neuron.
The model neuron, constructed in NEURON, includes all of the known ionic currents in these cells and receives synaptic input from
simulated spike trains via NMDA, AMPA, and GABAA receptors. After tuning the model by adjusting maximal current conductances in
each compartment, the model cell closely matched whole-cell recordings from an adult rat NAcb slice…We describe a computational model of the principal cell in the nucleus accumbens (NAcb), the medium spiny projection (MSP) neuron.
The model neuron, constructed in NEURON, includes all of the known ionic currents in these cells and receives synaptic input from
simulated spike trains via NMDA, AMPA, and GABAA receptors. After tuning the model by adjusting maximal current conductances in
each compartment, the model cell closely matched whole-cell recordings from an adult rat NAcb slice preparation. Synaptic inputs in the
range of 1000 –1300 Hz are required to maintain an “up” state in the model. Cell firing in the model required concurrent depolarization
of several dendritic branches, which responded independently to afferent input. Depolarization from action potentials traveled to the tips
of the dendritic branches and increased Ca2? influx through voltage-gated Ca2? channels. As NMDA/AMPA current ratios were increased,
the membrane showed an increase in hysteresis of “up” and “down” state dwell times, but intrinsic bistability was not observed.
The number of oscillatory inputs required to entrain the model cell was determined to be ?20% of the “up” state inputs. Altering the
NMDA/AMPA ratio had a profound effect on processing of afferent input, including the ability to entrain to oscillations in afferent input
in the theta range (4 –12 Hz). These results suggest that afferent information integration by the NAcb MSP cell may be compromised by
pathology in which the NMDA current is altered or modulated, as has been proposed in both schizophrenia and addiction.Other authorsSee publication -
A new bursting model of CA3 pyramidal cell physiology suggests multiple locations for spike initiation.
Biosystems/Elsevier
We introduce a novel computational model of hippocampal pyramidal cells physiology based on an up-to-date, detailed description of passive and active biophysical properties and real dendritic morphology. This model constitutes a modification of a previous (1995) model which included complex calcium dynamics and Na( ), K( ), and Ca(2 ) currents. Changes reflect recently acquired experimental knowledge regarding the types and spatial distributions of these currents. The updated model responds to…
We introduce a novel computational model of hippocampal pyramidal cells physiology based on an up-to-date, detailed description of passive and active biophysical properties and real dendritic morphology. This model constitutes a modification of a previous (1995) model which included complex calcium dynamics and Na( ), K( ), and Ca(2 ) currents. Changes reflect recently acquired experimental knowledge regarding the types and spatial distributions of these currents. The updated model responds to simulated somatic current clamp stimulation with a train of spikes (burst). The shape of the burst reproduces the characteristic behavior observed experimentally, similarly to the previous model. However, an analysis of dendritic membrane voltage distribution during the burst shows that the mechanisms underlying this somatic behavior are dramatically different in the two models. In the previous model, all spikes were generated in the soma and backpropagated in the dendrites. In the updated model, in contrast, only the first spike is initiated somatically. The second somatic spike is preceded by a dendritic spike (triggered by the first spike backpropagation), which propagates both backward and forward, reaching the soma just before the rise of the second somatic spike. The third and fourth spikes are similarly caused by a complex spatio-temporal interplay between somatic and dendritic depolarization. These results suggest that the distribution of ionic currents recently characterized in hippocampal pyramidal cells can support both somatic and dendritic spike initiation. In addition, these simulations demonstrate that models with considerably different distributions of active conductances can reproduce the same experimental bursting behavior with distinct biophysical mechanisms.
Other authors -
Patents
-
Visualizing tissue activated by electrical stimulation
Issued US 8886332
A visualization of an area or volume of tissue activated during stimulation according to a set of stimulation parameters is generated. The area or volume of activation is modeled based on a non-uniform grid of model neurons. Select portions of the grid have the model neurons more closely spaced, resulting in finer resolution graphical representation, while less closely spaced model neurons in other portions of the grid may avoid additional computation time.
Other inventorsSee patent -
Electrical stimulation programming
Issued US 8761890
In one example, the disclosure relates to a method comprising receiving at least one electrical stimulation parameter value defining electrical stimulation for delivery via one or more electrodes to a tissue site, and determining, via one or more processors, a volume of sub-activation threshold impact for tissue from the delivery of the electrical stimulation to the tissue site.
Other inventorsSee patent
Projects
-
"Fighting Crime with SPSS and Weather Data" oral presentation at IBM World of Watson 2016
To learn more about crime and determine ways to fight it, we mined San Francisco crime data using IBM SPSS Modeler and machine learning methods. But what happened when we incorporated data provided by The Weather Company was as unexpected as the weather
Other creatorsSee project
Honors & Awards
-
Star of Excellence Award
Medtronic Neuromodulation
For leading the Predictive Modeling Team: Data Sciences and Modeling. The award recognizes extraordinary job performance, hard work and an unwavering commitment to excellence. The Star of Excellence Award is Medtronic’s highest Quality and Innovation Award.
Languages
-
English
Full professional proficiency
-
Polish
Native or bilingual proficiency
Organizations
-
Project Management Institute
-
- Present -
Organization for Computational Neurosciences
Reviewer for the Computational Neuroscience Conference since 2004
- Present -
American Association for the Advancement of Science
-
-
Association for Computing Machinery
-
-
Association for the Advancement of Medical Instrumentation
-
-
Institute of Electrical and Electronics Engineers
-
-
Mensa
-
-
Society For Neuroscience
-
Recommendations received
16 people have recommended Maciej
Join now to viewMore activity by Maciej
-
Delighted to announce our investment into qomodo, a UK company securing industrial IoT devices against various cyber vulnerabilities. More and more…
Delighted to announce our investment into qomodo, a UK company securing industrial IoT devices against various cyber vulnerabilities. More and more…
Liked by Maciej Lazarewicz
-
Change the story, change the world. 40 years ago Medical Alley was formed to tell the world that Minnesota is the epicenter of health innovation and…
Change the story, change the world. 40 years ago Medical Alley was formed to tell the world that Minnesota is the epicenter of health innovation and…
Liked by Maciej Lazarewicz
-
✅ Bucket list item complete: delivered a lecture at Oxford on skillfulness in product design! Thanks to superhost Tim Denison, Ph.D. and the…
✅ Bucket list item complete: delivered a lecture at Oxford on skillfulness in product design! Thanks to superhost Tim Denison, Ph.D. and the…
Liked by Maciej Lazarewicz
-
What is the right SCS dose? It depends on the rate! As the rate goes up, the range of useful SCS amplitudes shrinks. Too much stimulation with tonic…
What is the right SCS dose? It depends on the rate! As the rate goes up, the range of useful SCS amplitudes shrinks. Too much stimulation with tonic…
Liked by Maciej Lazarewicz
-
So proud that Inceptiv is now FDA approved! The science and engineering that went into the ECAP amplifiers and signal chain, closed-loop…
So proud that Inceptiv is now FDA approved! The science and engineering that went into the ECAP amplifiers and signal chain, closed-loop…
Liked by Maciej Lazarewicz
-
Dr. Andrew Ng joined Amazon's Board of Directors 👏 https://lnkd.in/g-Mz5u_2 #ai #amazon
Dr. Andrew Ng joined Amazon's Board of Directors 👏 https://lnkd.in/g-Mz5u_2 #ai #amazon
Liked by Maciej Lazarewicz
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More