logo

Neuromatch Academy: Deep Learning (Experimental)
  • Introduction
  • Schedule
    • General schedule
    • Shared calendars
    • Timezone widget
  • Technical Help
    • Using jupyterbook
      • Using Google Colab
      • Using Kaggle
    • Using Discord
  • Quick links and policies
  • Prerequisites and preparatory materials for NMA Deep Learning

Basics Module

  • Basics And Pytorch (W1D1)
    • Tutorial 1: PyTorch
  • Linear Deep Learning (W1D2)
    • Tutorial 1: Gradient Descent and AutoGrad
    • Tutorial 2: Learning Hyperparameters
    • Tutorial 3: Deep linear neural networks
    • Bonus Lecture: Yoshua Bengio
  • Multi Layer Perceptrons (W1D3)
    • Tutorial 1: Biological vs. Artificial Neural Networks
    • Tutorial 2: Deep MLPs

Fine Tuning

  • Optimization (W1D5)
    • Tutorial 1: Optimization techniques
  • Regularization (W2D1)
    • Tutorial 1: Regularization techniques part 1
    • Tutorial 2: Regularization techniques part 2
  • Deep Learning: The Basics and Fine Tuning Wrap-up

ConvNets and Generative Models

  • Convnets And Dl Thinking (W2D2)
    • Tutorial 1: Introduction to CNNs
    • Tutorial 2: Deep Learning Thinking 1: Cost Functions
    • Bonus Lecture: Kyunghyun Cho
  • Modern Convnets (W2D3)
    • Tutorial 1: Learn how to use modern convnets
    • Bonus Tutorial: Facial recognition using modern convnets
  • Generative Models (W2D4)
    • Tutorial 1: Variational Autoencoders (VAEs)
    • Tutorial 2: Diffusion models
    • Tutorial 3: Image, Conditional Diffusion and Beyond
    • Bonus Lecture: Geoffrey Hinton

Natural Language Processing

  • Attention And Transformers (W2D5)
    • Tutorial 1: Learn how to work with Transformers
    • Bonus Tutorial: Understanding Pre-training, Fine-tuning and Robustness of Transformers
  • Time Series And Natural Language Processing (W3D1)
    • Tutorial 1: Introduction to processing time series
    • Tutorial 2: Natural Language Processing and LLMs
    • Bonus Tutorial: Multilingual Embeddings
  • Dl Thinking2 (W3D2)
    • Tutorial 1: Deep Learning Thinking 2: Architectures and Multimodal DL thinking
  • Deep Learning: Convnets and NLP

Unsupervised and Reinforcement Learning

  • Unsupervised And Self Supervised Learning (W3D3)
    • Tutorial 1: Un/Self-supervised learning methods
    • Bonus Lecture: Melanie Mitchell
  • Basic Reinforcement Learning (W3D4)
    • Tutorial 1: Basic Reinforcement Learning
    • Bonus Lecture: Chealsea Finn
  • Reinforcement Learning For Games And Dl Thinking3 (W3D5)
    • Tutorial 1: Reinforcement Learning For Games
    • Tutorial 2: Deep Learning Thinking 3
    • Bonus Tutorial: Planning with Monte Carlo Tree Search
    • Bonus Lecture: Amita Kapoor

Deploy Models on the Web

  • Deploy Models (Bonus)
    • Bonus Tutorial: Deploying Neural Networks on the Web

Project Booklet

  • Introduction to projects
  • Daily guide for projects
  • Modeling Step-by-Step Guide
    • Modeling Steps 1 - 2
    • Modeling Steps 3 - 4
    • Modeling Steps 5 - 6
    • Modeling Steps 7 - 9
    • Modeling Steps 10
    • Example Data Project: the Train Illusion
    • Example Model Project: the Train Illusion
    • Example Deep Learning Project
  • Project Templates
    • Computer Vision
      • Slides
      • Ideas
      • Knowledge Extraction from a Convolutional Neural Network
      • Music classification and generation with spectrograms
      • Something Screwy - image recognition, detection, and classification of screws
      • Data Augmentation in image classification models
      • Transfer Learning
    • Reinforcement Learning
      • Slides
      • Ideas
      • NMA Robolympics: Controlling robots using reinforcement learning
      • Performance Analysis of DQN Algorithm on the Lunar Lander task
      • Using RL to Model Cognitive Tasks
    • Natural Language Processing
      • Slides
      • Ideas
      • Twitter Sentiment Analysis
      • Machine Translation
    • Neuroscience
      • Slides
      • Ideas
      • Animal Pose Estimation
      • Segmentation and Denoising
      • Load algonauts videos
      • Vision with Lost Glasses: Modelling how the brain deals with noisy input
      • Moving beyond Labels: Finetuning CNNs on BOLD response
      • Focus on what matters: inferring low-dimensional dynamics from neural recordings
  • Models and Data sets
Powered by Jupyter Book
  • repository
  • open issue
  • .md
Contents
  • Quick links
  • Policies
    • Coursework attendance policy
    • Projects attendance policy

Quick links and policies

Contents

  • Quick links
  • Policies
    • Coursework attendance policy
    • Projects attendance policy

Quick links and policies¶

Quick links¶

Course materials: https://deeplearning.neuromatch.io/

Portal: https://portal.neuromatchacademy.org/

Website: https://academy.neuromatch.io/

Crowdcast: https://www.crowdcast.io/e/neuromatch-academy-2022-

Code of Conduct and Code of Conduct Violations Form: https://github.com/NeuromatchAcademy/precourse/blob/main/CODE_OF_CONDUCT.md

Project Exemption Form: https://airtable.com/shrubhlgsWJ8DuA7E

Attendance Exemption Form: https://airtable.com/shrJdpfwACARN5Jop

Policies¶

Coursework attendance policy¶

Students who participate in this course will gain a certificate of completion for the coursework. Students are allowed to miss two days if necessary and if they communicate that with their teaching assistant. If there are exceptional circumstances that force a student to miss class for reasons completely beyond their control, such as severe illness, electricity blackouts, etc, they can request to get the certificate despite missing more than two days by filling out the attendance exemption form (https://airtable.com/shrJdpfwACARN5Jop) at least two days prior to the end of course. Please note these requests may not be granted.

Projects attendance policy¶

Projects are an integral part of the Neuromatch Academy experience. Students who participate in projects and miss no more than two days of projects work will gain a certificate of completion for the projects.

If there are exceptional circumstances that make it difficult to attend the projects portion of the course, students can request to drop out of projects by filling out the project exemption form (https://airtable.com/shrubhlgsWJ8DuA7E). If their request is granted, the student can continue to attend the coursework sections and gain a coursework certificate if eligible (see above), but not participate in the projects work.

If the student participates in projects but misses more than two days due to exceptional circumstances, they can request to get the projects certificate anyway by filling out the attendance exemption form (https://airtable.com/shrJdpfwACARN5Jop) at least two days prior to the end of course. Please note these requests may not be granted.

previous

Using Discord

next

Prerequisites and preparatory materials for NMA Deep Learning

By Neuromatch

The contents of this repository are shared under under a Creative Commons Attribution 4.0 International License. Software elements are additionally licensed under the BSD (3-Clause) License.