Bringing insights from the brain to machine learning.
Theoretical neuroscientist at Stanford.

About Me

In a fraction of a second our brain captures information about our world and effortlessly extracts meaning from this sensory information. What exactly are the computations these neural circuits are performing? Are there general principles for understanding how neural systems are processing information, given the input statistics for instance? And can the answers to these questions inform how we build artificially intelligent systems like deep learning networks?

I am a PhD candidate at Stanford where I do a mix of theory and experimental tests of theory in order to get at these questions. My PhD research focuses on predictive inference and coding in the early stages of vision, and brings together tools from machine learning, information theory, high-dimensional data analysis, and nonequilibrium physics.

Curriculum Vitae


  • 2012-Present

    Stanford University
    Ph.D. Neuroscience
    Ph.D. Minor Computer Science

    Advisors: Baccus and Ganguli Labs
    Top 10% Poster Award, CS231N CNNs
    Mind, Brain, and Computation Traineeship
    NSF IGERT Graduate Fellowship

  • 2010-2012

    University of Hawaii
    M.A. Mathematics

    Advisor: Susanne Still, Machine Learning Group
    Departmental Merit Award
    NSF SUPER-M Graduate Fellowship
    Kotaro Kodama Scholarship
    Graduate Teaching Fellowship

  • 2006-2010

    University of Chicago
    B.A. Computational Neuroscience

    Research: MacLean Comp. Neuroscience Lab
    Research: Dept. of Economics Neuroecon. Group
    Research: Gallo Memory Lab
    Lerman-Neubauer Junior Teaching Fellowship
    NIH Neuroscience and Neuroengineering Fellowship
    Innovative Funding Strategy Award

  • 2009

    Institute for Advanced Study
    Undergraduate Research Fellow

    Bioinformatics research at Simons Center for Systems Biology in Princeton, NJ

  • Past-2006

    Originally from
    San Diego

    Bank of America Mathematics Award
    President's Gold Educational Excellence Award
    California Scholarship Federation Gold Seal
    Advanced Placement Scholar with Distinction


A Deep Learning Model of the Retina

In just three layers of cells, the retina encodes the visual world into a binary code of action potentials that conveys information about motion, object edges, direction, and even predictions about what will happen next in the world. In this paper we use convolutional neural networks to create the most accurate model to-date of retinal responses to spatiotemporally varying binary white noise, and provide a foundation for predicting retinal responses to natural scenes. We also investigated how well convolutional neural networks in general can recover simple, sparse models on high dimensional data.
Lane McIntosh, Niru Maheswaranathan
Top 10% Poster Award, CS231n Convolutional Neural Networks, 2015
In Preparation, 2015

PDF Poster Github

Multiple Spatial Scales of Inhibition Improve Information Transmission in the Retina

Retinal ganglion cells, the bottleneck of all visual information to the brain, have linear response properties that appear to maximize information between the visual world and the retinal ganglion cell responses, subject to a variance constraint. In this paper I contribute a new theoretical finding that generating the ganglion cells' linear receptive field from inhibitory interneurons with disparate spatial scales provides a basis that allows the receptive field to maximize information under a wide range of environments whose signal-to-noise ratios vary by orders of magnitude.
Mihai Manu, Lane McIntosh, David Kastner, Benjamin Naecker, and Stephen Baccus
In Preparation, 2015

SfN 2015 Poster Github

Video-based Event Recognition

How can we automatically extract events from video? We used a database of surveillance videos and examined the performance of SVMs and Convolutional Neural Networks in detecting events like people getting in and out of cars.
Ian Ballard* and Lane McIntosh*
CS221 Artificial Intelligence Poster, 2014

PDF Poster

Learning Predictive Filters

How should an intelligent system intent on only keeping information predictive about the future filter its data? We analytically find the optimal predictive filter for Gaussian input using recent theorems from the information bottleneck literature. Using numerical methods, we then show the resemblance of these optimally predictive filters to the receptive fields in early visual pathways of vertebrates.
Lane McIntosh
CS229 Machine Learning Poster, 2013

PDF Poster

Thermodynamics of Prediction in Model Neurons

Recent theorems in nonequlibrium thermodynamics show that information processing inefficiency provides a lower bound for energy dissipation in certain systems. We extend these results to model neurons and find that adapting neurons that match the timescale of their inputs perform predictive inference while minimizing energy inefficiency.
Lane McIntosh and Susanne Still
Master's Thesis, 2012

PDF Github


Math Tools For Neuroscience

Math Tools for Neuroscience

Stanford University, Spring 2015. Co-taught this class with fellow graduate student Kiah Hardcastle, and covered a wide variety of useful mathematical tools including dimensionality reduction, Fourier transforms, dynamical systems, statistics, information theory, and Bayesian probability. Mostly graduate student and postdoctoral audience.

Intro to Perception

ExploreCourses Listing

Stanford University, Fall 2014. Teaching assistant for this introductory undergraduate course surveying the literature on perception from the retina to high-level cortex and behavioral experiments.


Precalculus Course Website

University of Hawaii, 2010-12. First a teaching assistant, then lecturer, for this large undergraduate introductory mathematics course.

Biophysics and Chemical Biology

University of Chicago, Spring 2008. Teaching assistant for the third course in the advanced-track biology sequence for students who scored 5/5 on their AP Biology test. This course focused on how to read original research papers in biophysics and chemical biology, with weekly presentations.