Deep Learning – Spring 2022

Class Hours

Tue: 5:00 pm — 5:30 pm:, Thur: 7:15 pm — 8:45 pm
Location LT:1

Office Hours and Contact Info.

Instructor: Mohsen Ali
Office Hours; to be announced
Email: mohsen.ali@itu.edu.pk

Teaching Assistant 1: Hafiz Muhammad Arslan
Office Hours: Monday & Wednesday 2:00 to 4:00 pm
Email: msds20044@itu.edu.pk

Teaching Assistant 2: Muhammad Sohail Danish
Office Hours: Tuesday 2:00 pm to 3:30 pm
Email: msds20004@itu.edu.pk

Course Basics

Core Course
Credit Hours: 3
Being offered to both MSDS, MSCS, and BS students
Practical and hands-on approach
5 to 6 programming assignments

Prerequisite

Enthusiasm, Energy, and Imagination
Data Structures, Probability & Statistics, Linear Algebra and basic Calculus
Programming skills and desire to read & implement.

Course Overview

We are going to take the “get your hands dirty” approach, you will be given assignments and projects to implement ideas discussed in the class. Projects and assignments will contain miniature versions of real-life existing applications and problems (e.g can you train your computer to generate dialogues in Shakespeare style or convert your image into painting as done by Monet, sentiment analysis, etc.. ).
The course will concentrate on developing both mathematical knowledge and implementation capabilities. We will start from training a single perceptron, move to training a deep neural network, study why training large networks is a problem and what could be its possible solutions. After dipping our toes in deep belief networks and recurrent neural network we will start looking into applications of deep learning in three different areas, text-analysis, speech processing, and computer vision. The objective of this approach is to make you comfortable enough that you can understand various research problems and, if interested, can implement deep learning-based applications.

Course Objectives

In the last few years, machine learning has matured from science fiction to reality. We are living in a world where we have already seen industry bringing to reality self-driving cars, face-recognizers that work on a massive scale (Facebook), speech translation systems that can translate from one language to many other simultaneously and in real-time, and more interestingly we have machines that can learn to play atari games in a similar fashion as we do.
A lot of these victories have come from the exciting field of Deep Learning; a learning methodology based on the concept that the human mind captures details at multiple levels or at multiple abstract levels. One property of deep learning is removing the responsibility of humans to design features, instead, Deep Learning is given a task to find the appropriate representation.

Grading Policy

45% Assignments
5% Class participation and Creating Notes
20% Final Project
10% Quizzes
10% Midterm Exam
10% Final Exam

Honor Code

All cases of academic misconduct will be forwarded to the disciplinary committee. All assignments are group-based unless explicitly specified by the instructor. In the words of Efros, let’s not embarrass ourselves.

Tentative and Rough Course Outline

Weeks	Topics	Evaluations
1	Introduction to Deep Learning Difference between Machine Learning and Deep Learning Basic Machine Learning: Linear & Logistic Regression,
2	Supervised Learning with Neural Networks Deep Learning, Single and Multi-Layer Neural Networks, Perceptron Rule, Gradient Descent, Backpropagation, Loss Functions Tutorial 1: Python/Numpy Tutorial/Anaconda
3	Hyperparameters tuning, Regularization and Optimization Parameters vs Hyperparameters, Why regularization reduces overfitting? Data Augmentation, Vanishing/Exploding gradients, Weight Initialization Methods, Optimizers Tutorial 2: Building a Linear Classifier
4	Convolutional Neural Networks Convolutional Filters, Pooling Layers, Classic CNNs: AlexNet, VGG, GoogleNet, ResNet, DenseNet. Transfer Learning Tutorial 4: CNN Visualization
5	Deep Learning for Vision Problems Object Localization & Detection, Bounding box predictions, Anchor boxes, Region Proposal Networks, Detection Algorithms: RCNN, Faster RCNN, Yolo, SSD. Tutorial 5: Caffe & Object Detection
6	Sequence Models Recurrent Neural Networks (RNN), Gate Recurrent Unit (GRU), Long Short Term Memory (LSTM), Bidirectional RNN, Backpropagation through time. Image Caption Generation, Machine Translation, Text Generation & Summarization and Transformers Tutorial 6: Image Captioning & Text Generation
7	Auto-Encoders & Generative Models Variational Auto-Encoders, Stacked Auto-Encoders, Denoising Auto-Encoders, Concept of Generative Adversarial Networks (GANs)
8	Miscellaneous Deep Networks Generalization, Adversarial Examples and Attacks, Reinforcement Learning, Capsule Networks, Convolutional LSTM, Attention Networks, Restricted Boltzmann Machine, One-Shot Learning, Siamese Networks, Triplet Loss, Graph CNN, Approximate and Energy-Efficient Design for Deep CNN (Dr. Rehan Hafiz)

	Topics	Notes / Reading Material / Comments	News
09th Mar 2021	Introduction	45% Assignments 20% Final Project 5% Class participation and Creating Notes 10% Quizzes 10% Midterm Exam 10% Final Exam
09th Mar 2021	Recommended Resources	Text Book Deep Learning by Ian Goodfellow Link Dive into Deep Learning by Aston Zhang and co. Link Recommended Online Books http://deeplearning.net/ http://neuralnetworksanddeeplearning.com/ Courses Machine Learning, Oxford – Nando de Freitas Link Convolutional Neural Networks for Visual Recognition, Stanford (cs231n) Link A curated list of courses (Recommended) Link Deep Learning for Natural Language Processing, Stanford Link Video Lectures Essence of Neural Networks – 3Blue1Brown Link Convolutional Neural Networks for Visual Recognition, Stanford (cs231n) – Video Lectures Link Neural Networks and Deep Learning – deeplearning.ai – Link
11th Mar 2021	Un-Supervised and Supervised Learning Linear Regression	Introduction Learning: Supervised, unsupervised. Learning: discontinuous, continuous Models: bias and variance Linear Regression Error Function in Linear Regression Assigned Readings: CMU Deep Learning Course Learning the Network-slides by Andrew NG Page 1-4, and 16-19 Recommended Readings: Section 5.1 to 5.4 from the textbook Python Numpy Tutorial http://deeplearning.cs.cmu.edu/S21/index.html Python Crash Course: https://learnxinyminutes.com/docs/python/ Python Intermediate: https://pythonbasics.org/ Refresh: Concepts of local minima, local maxima, convex functions, concave functions, critical points, chain rule, saddle point
16th Mar 2021	No Class	Makeup class will be announced soon
18th Mar 2021	No Class	Makeup class(es) will take place on Saturday 27th March, 2021
23rd Mar 2021	No Class on account of Pakistan Resolution Day	Makeup class will be announced soon
25th Mar 2021	Linear Regression	Linear Regression Where to use the Machine Learning? What basic points to ask? Problem / objective Data Model that satisfies the objective Parameters of the model Loss function How to optimize the loss function. Error Function in Linear Regression What are the convex functions? Concept of local and global minima & maxima, saddle point Optimization Differentiation/gradient Critical points Differentiation in single variable case More than one variable Hessian, semi-positive definite How to find maxima? Assigned Readings: CS299 Lecture Notes by Andrew NG Page 1-4, and 16-19 Section 5.1 to 5.4 from the textbook Recommended Readings: http://deeplearning.cs.cmu.edu/S21/document/slides	Assignment 1
27th Mar 2021	Optimization, Gradient Descent and Logistic Regression	Discussed Topics: Concepts of local minima, local maxima, convex functions, concave functions, critical points, chain rule, saddle point Models: bias and variance Gradient descent update rule is derived using taylor series expansion. For details https://towardsdatascience.com/mathematical-intuition-behind-gradient-descent-f1b959a59e6d Taylor series is a method to approximate functions using its derivatives. https://www.youtube.com/watch?v=3d6DsjIBzJ4 https://www.cs.princeton.edu/courses/archive/fall18/cos597G/lecnotes/lecture3.pdf Logistic Regression Error Function in Logistic Regression Recommended Readings and Tutorials: Section 5.1 to 5.4 from the textbook http://deeplearning.cs.cmu.edu/S21/document/slides Recommended Reading on Logistic Regression http://peterroelants.github.io/posts/neural_network_implementation_part02/ https://www.youtube.com/playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab Recommended Readings: Gradient Descent: Video Lecture from Coursera, Andrew NG
30th Mar 2021	Logistic Regression, Classification, Loss Functions	Classification Linear Classification Binary Classification using logistic regression Logistic Regression Squashing function Sigmoid Cross Entropy loss function Classification and its link with probability Maximum likelihood Estimation Multi-class classification Softmax Take home task Compute gradient of the cross entropy loss function with soft-max. Is cross-entropy loss function with soft-max a convex function Assigned Readings: Video Lecture by Nando de Freitas Lecture 7: Logistic regression Video Link Slides Handout: Training a Classifier by Roger Grosse Recommended Reading: Softmax and Cross Entropy https://deepnotes.io/softmax-crossentropy http://knet.readthedocs.io/en/latest/softmax.html Assigned Readings (Linear Algebra): Linear Algebra from book Deep Learning Linear algebra cheat sheet for deep learning Linear Algebra for Machine Learning
1st Apr 2021	Multi Class Classification, Optimization and Gradient Descent	Multi-class classification Softmax and cross entropy loss. Why is softmax used but not sigmoid? Optimization of loss function Learning Rate Momentum Gradient Descent Stochastic Gradient Descent Batch Gradient descent Minibatch Gradient Descent Gradient Descent Optimization Algorithms Momentum Adagrad Adadelta RMSprop Adam AdaMax Visualization of Algorithms Which optimizer to use? Recommended Readings: https://towardsdatascience.com/a-look-at-gradient-descent-and-rmsprop-optimizers-f77d483ef08b Recommended Readings: Gradient Descent: Video Lecture from Coursera, Andrew NG
2nd Apr 2021	Neural Networks	Feed-forward Neural Networks Perceptron OR-Function AND-Function XOR-Function Multiple Perceptron Multiple Layer Neural Network Nonlinear classification (circle) Role of activation functions hard-limit, sigmoid, tanh, ReLu, leaky ReLu, MaxOut, ELU Input, output and hidden layers Why do we need non-linear activation functions? Forward pass as matrix multiplication. Decision Boundaries Assigned Readings: Chapter 6: Deep Forward Networks; Book: Deep Learning by Ian Upto complete section 6.3. Activation Functions: Neural Networks CS231- Neural Network-1 Recommended Readings: Perceptron Rule Reading: few Section 4-1 to Section 4-13 Single-layer Neural Networks (Perceptrons) by Dr. Humphrys Optionally: Online Learning and the Perceptron Algorithm from Andrew NG
3rd Apr 2021	Backpropagation	How to determine Weights? Chain Rule Back-propagation Algorithm Training Neural Networks Assigned Readings: Chapter 6: Deep Forward Networks; Book: Deep Learning by Ian Goodfellow. Section 6.5 complete. Recommended Readings Chapter 2: How the backpropagation algorithm works, Book: Neural Networks and Deep Learning by Michael Nielson, Notes on Backpropagation by Peter Sadowski, Department of Computer Science Optional: How to do backpropagation in a brain by Hinton Video Lecture: Lecture 4: Backpropagation; Dhruv Batra Lecture 10 – Neural Networks, Yaser Abu-Mostafa.
6th Apr 2021	Neural Network Training	How to determine Weights? Chain Rule Back-propagation Algorithm Weights Initialization Techniques Activation Functions Relu Sigmoid Tanh Swish Leaky Relu Elu Assigned Readings: Chapter 6: Deep Forward Networks; Book: Deep Learning by Ian Goodfellow. Page 204 to 227 CS231- Neural Network-1 Activation Functions: Neural Networks Deep Learning – Yann LeCun	Assignment 2
8th Apr 2021	Weight Initialization and Batch Normalization	Weight Initialization Random Initialization. Initialize Weights using Gaussian Distribution. If you are using ReLU activation use Kaiming/MSRA method. If you are using tanh activation use Xavier Initialization method. Covariate Shift During training updating weights of layers affects distribution of each layer’s inputs. This is also called covariate shift. Batch Normalization. It used to tackle covariate shift problems in data. Improves gradient flow. Makes deeper networks to train much easier. Allow higher learning rates, faster convergence Assigned Readings Batch Normalization Paper Recommended Reading: https://machinelearningmastery.com/batch-normalization-for-training-of-deep-neural-networks/
13th Apr 2021	Regularization and Dropout	Capacity of Network Overfitting How to avoid overfitting Regularization Bias/Variance, overfitting, underfitting L2 /L1 regularization Drop Out Concept of stochastic regularization Forward / backward Help Network in converging. Data Augmentation Learning Rate decay Home Work: Nuclear Norm L0 norm Assigned Readings: Dropout Paper Paper on Dropout and Model uncertainty Video Lectures Deep Learning – Lecture 4 – Nando de Freitas – Link Recommended Readings: A Recipe for Training Neural Networks
15th Apr 2021	Texture and Convolution filters	Texture Texture/ pattern Why is texture important? How to represent texture? Texture can be useful in image recognition Convolution Convolution of two signals in continuous time Convolution in discrete time Convolution in image processing Image Filtering Applying filter on images using convolution Box filter Sharpening Filters
20th Apr 2021	Filters and Convolutional Neural Networks	Image Gradient Derivative Filters Double Derivative filters Gaussian Filters Blob detection Filter Banks Filters to detect edges Filters to detect bars Filters to detect blobs What does CNNs learn? Convolution is shift Invariant Convolutional Neural Networks Why do we need convolutional neural networks? Building blocks of CNN Convolutional Layer Pooling Layer Activation Function ReLU NOTES Image Filtering and Texture (SLIDES) How Does CNN work? (SLIDES) Assigned Readings Convolutional Networks, Roger Grosse Recommended Readings Convolutional Neural Networks For All \| Part I Convolutional Neural Networks For All \| Part II
22th Apr 2021	CNNs	Making Deep neural Networks using convolution and pooling layers. Hyper parameters in CNN Number of layers Size of features Pooling window size Stride Number of neurons in fully connected layers What is a Receptive Field? How it is important for object recognition Relationship with filter size, depth How does a receptive field affect accuracy? Increasing receptive field Using dilated convolutions Max Pooling 1×1 Convolution Feature Fusion, Dimensionality reduction or bottleneck layer. Assigned Readings Computing Receptive Fields of Convolutional Neural Networks, Araujo et. al. , Distill, 2019 Understanding the Effective Receptive Field in Deep Convolutional Neural Networks, Luo et. al., Advances in neural information processing systems, 2016
27th Apr 2021	Back Propagation in CNNs	Backpropagation for Convolutional layer Backpropagation for Pooling layer Converting a FC layer to the Convolutional Layer Reference Backpropagation In Convolutional Neural Networks Convolutional Neural Networks backpropagation: from intuition to derivation Convolutions and Backpropagations – Pavithra Solai Video Lecture: https://www.youtube.com/watch?v=uCMd1PmJQ6w&feature=youtu.be https://www.youtube.com/watch?v=BvrWiL2fd0M&feature=youtu.be	Assignment 3 Deliverable 2
29th Apr 2021	Transfer Learning	Transfer Learning Layers and hierarchical feature learning Freezing and Fine-tuning Le-Net, AlexNet, VGG, Inception Net, ResNet Larger Models and Parameters Larger models means more number of layers and deeper models. More parameters mean we need large data to train and overfitting if we do not have enough data. Larger models have greater learning capacity Large number of parameters also increase chances of overfitting. Link with receptive field 1*1 convolution is used for the receptive field to stay the same.	Assignment 3 Deliverable 1
4th May 2021	Transfer Learning and CNN Architectures	Padding types Vanishing and exploding gradient problem in training of large networks. Use of residual Blocks to help in flow of gradients. Residual Blocks Skip layers Using bottle neck layer to reduce computation Different Network Types AlexNet VGG Inception ResNet DenseNet GoogLeNet Semantic segmentation Groups of pixels of same class It is classification problem at pixel level Fully connected convolutional networks Assigned Reading A guide to convolution arithmetic for deep learning Convolutional Networks – Chapter 9 Section: 9.1, 9.2 Famous CNN-architectures AlexNet, VGGNet, ResNet, DenseNet ImageNet Classification with Deep Convolutional Neural Networks; Alex Krizhevsky, NIPS 2012 aka Alexnet Recommended Readings Convolutional Networks – Chapter 9 Section: 9.3, 9.4, 9.5, 9.8, 9.9
6th May 2021	Semantic Segmentation	CNN for Semantic Segmentation Deconvolution Upscaling-convolution Fully Convolutional Network Semantic segmentation Groups of pixels of same class It is classification problem at pixel level Object Detection Classification Assigned Reading Survey on Image Segmentation using Deep Learning Recommended Readings Implementation of Image Segmentation using Mask RCNN Fully Convolutional Networks for Semantic Segmentation
18th May 2021	Localization and Object Detection	Localization How localization is different from classification Localization as regression problem Bounding box regression Classification head Regression head Object Detection Object detection as classification and localization Using regression and localization head for object detection Intersection over Union Sliding window method Region Proposal method Non Maximum Suppression Selective search Single stage detectors Yolo SSD Two stage detector RCNN MaskRCNN Interesting Project Topics Transformers Graph Neural Networks Self-supervised learning Semi-Supervised Learning Zero shot Learning Few Shot Learning Recommended Readings Yolo, SSD, RCNN, Mask RCNN, Transformers Paper	Assignment 4
20th May 2021	Object Detection, Recurrent Neural Networks	Sliding Window approach without anchors. Sliding Window approach with anchors. Two-stage detectors Fast RCNN Faster RCNN Single Stage detectors Yolo SDD Retina net Feature Pyramid Networks Negative Hard Mining Sequence Modelling Many to one e.g Sentiment Classification Many to many e.g. Translation One to many e.g image to caption Recurrent Neural Networks Output dependent on current input and previous hidden state Backpropagation through time Vanishing/Exploding gradients Gated cells allow previous hidden states to bypass current cell Assigned Reading Sequence Modeling: Recurrent and Recursive Nets, Chapter 10 from textbook. Recommended Readings Faster RCNN, Fast RCNN, Retina net
1st June 2021	Language Models	Basic Neural Language Model Conditional Language Model Wordtovec One hot encoding Distributed vector representations Bidirectional RNN Transformation Architecture Evaluation criteria for caption generation Autoencoders Encoder RNN Decoder RNN Recommended Readings Visualizing memorization in RNNs https://distill.pub/2019/memorization-in-rnns/ Just understand how different setups are different from each other. https://ofir.io/Neural-Language-Modeling-From-Scratch/ https://towardsdatascience.com/the-beginners-guide-to-language-models-aa47165b57f9 https://medium.com/phrasee/neural-text-generation-generating-text-using-conditional-language-models-a37b69c7cd4b
3rd June 2021	Unsupervised Learning	Unsupervised Learning Principal Component Analysis Clustering Kmeans Clustering Cluster Centres Cluster association Coordinate Descent Algorithm Generative Models Autoregressive generative models Pixel RNN paper Autoencoders Hugo Larochelle’s lectures are treat – Slides https://www.youtube.com/watch?v=FzS3tMl4Nsc Readings Understanding Dimension Reduction with Principal Component Analysis (PCA) Dimensionality Reduction A Short Tutorial, Ali Ghodsi In tutorial understand the Table 1.1. Chapter 14: Autoencoders from Deep Learning book
8th June 2021	Autoencoders	The Autoencoder Principal Output image is same as input image First input is encoded than it is decoded Latent representation Types of different Autoencoder Denoising Autoencoder Sparse Autoencoder Variational Autoencoder Variational Inference KL Divergence
10th June 2021	Generative Adversarial Networks	Generative Adversarial Networks Two player game (Generator vs Discriminator) ProGAN CycleGAN StyleGAN DCGAN WGAN
15th June 2021	Do deep networks Generalize?	Do Deep nets Generalize? Distribution Shift Calibration Adversarial Examples Is it due overfitting Linear model hypothesis Adversarial Attacks Assigned Readings: CS182 Spring21 Lecture 20 Assigned Video Content: Lecture Sergey Levine Recommended Readings: What is a GAN? Paper: Generative Adversarial Networks Paper: DCGAN Wasserstein GAN Blog Post (From GAN to WGAN)
17th June 2021	Adversarial Attacks	Adversarial Attacks Changing loss function to deal with them Fast Gradient Sign Method Transferability of adversarial attacks Zero-Shot black-box attack Learning based control & imitation From prediction to control challenges Reinforcement learning Agents Concept of Reward function States observations	Assignment 5
24th June 2021	Reinforcement Learning	Deep learning in board games. Q-function: expected total reward Q-Learning Policy Learning Finding the policy that Maximizes the reward Policy gradients Alpha zero

Text Book

Text Book: Deep Learning by Ian Goodfellow Link
Reference Book: Dive into Deep Learning by Aston Zhang and co Link

Assignments

Projects

Project No.	Project Title	Name
001	Wheat Detection Challenge	Ibrahim Tariq, Arsalan Tahir, Shuja Mehmood, Abdul Rahman, Ahmad Haroon
002	Domain Adaptation (Wild Animal Detection)	Ch Hamza Jamil
004	Multi-lingual Caption Generation or Visual Q&A	Muhammad Hadi, Muhammad Sheraz, Hafiz Muhammad Usman
006	Wheat Detection Challenge	Abdullah Aziz, Rameesha Mahmood, Muhammad Mubashir Ali, Arslan Afzal, Ahmad Nawaz
007	Conversational Chat Bot	Ayman Ahmad, Niha Ramzan, Shan-e-Fatima
008	Text Summarization and Simplification	Abdur-Rub, Waleed Younas, Abdullah Riaz, Mukarram Ahmad, Hafiz Muhammad Zahid
010	Urdu text detection	Aamna Khan
011	Urdu Optical Character Recognition for Twitter screenshots	Hassan Khalid, Zubair Khalid, Ahmad Muzaffar, Rutaba Niazi
013	Contrastive Learning for Unpaired Image-to-Image Translation	Asghar Nazir, Shuja, M.Danish Bilal, A.Rehman, Mahnoor Imran
014	Visual Question Answering	Muhammad Umer Sani, Hira Ejaz, Naila Nawaz, Salman Ahmed, Muhammad Ahmed
016	Pneumonia Classification Using Deep Learning from Chest X-ray images	Hamza Arshad , Waleed Ahmad, Aimen Mushtaq, Nabeela Firdous, Hamid Ali
017	Facebook Hateful Meme Classification Challenge	Hamza Munir, Mehmood Ali, Agha Muhmmmad Anas, Hamza Nasir
018	“Hello” to “Bonjour”	Hafiz Zia Ahmad, Tariq Aman, Abdul Mateen, Azeem Ashraf, Sajjad Mustafa
019	Affective Computing, Emotion Transformation	Kinza Mehak, Maria Marrium, Muqarrub Rehman, Sheeza Shabbir, Sumbal Akram
020	Face Super-Resolution	Sohaib Ali Gill, M Akmal Masud, Bilal Rana, Abdul Malik
021	Landmark Detection	Muhammad Sufyan Ashraf, Mubashir ul Islam , Aqsa Khalid, Amna Shahbaz
022	Public Sentiment Analysis regarding COVID19 vaccines using tweets	AMNA ARSHAD, AMMARA RAFIQUE, SOHA ALI
023	Wheat Detection Challenge	Humza Sami, Mahnoor Sagheer, Muhammad Usama Zaki
024	Fake Face Detection	Muhammad Musharaf, Raja Sanwal Khan
025	Classifying Cardiac Abnormalities from twelve-lead ECGs	Qazi Danish, Muhammad Uzair, Hira Saleem, Aiman Younas, Khuzaima Shahid
026	Art Visual Question Answering	Ahmed Shahzad, Ans Munir, Maria Iqbal
027	Experimental Analysis of Colmap, NeRF and NeRF–	Hafiz Muhammad Arslan, Ahmad Bashir
028	Generating Avatar from Real Human Face Image using GAN	Bilal Ayub
029	Scene Graph Generation	Sohail Danish, Maham Ilyas, Hafiza Sidrah Bint E Jabran
030	Self-supervised Learning with GNN	Muhammad ali, Mahrukh, Shaaf abdullah, Zuhha azhar, Aliza Masood
031	Cross-view Image Geo-localization Using Deep Convolutional Neural Networks	Kinza Fayyaz, Syed Javed

￩￫ x

Deep Learning – Spring 2022

Class Hours

Office Hours and Contact Info.

Course Basics

Prerequisite

Course Overview

Course Objectives

Grading Policy

Honor Code

Tentative and Rough Course Outline

Course Notes

Text Book

Recommended Readings

Assignments

Assignment 1: Classification of MNIST Digits Using Pytorch:

Assignment 2: Implementation of Neural Network:

Assignment 3: Implementation of Convolutional Neural Network:

Assignment 4: Breaking Bread – Dataset Collection for Local Foods:

Assignment 5: Sentiment Analysis Using Sequence Models

Assignment 6 (Optional): Image Classification Competition

Some Interesting Links

Projects