Example AI Topics

A systems approach to AI

As its evident from all existing approaches towards AI, multidisciplinary science that aims to create agents that can think and act humanly or rationally. This course starts…

AI Agents

We will cover the agent-environment interface, the rational, learning agent architectures and a practical example of a robotic agent.

Pantelis Monogioudis

Backprop Workshop in Tensorflow

TensorFlow’s eager execution is an imperative programming environment that evaluates operations immediately, without building graphs. We are usually using the computational…

Backpropagation DNN exercises

Computational graph in Tensorboard showing the components involved in a TF BP update

Backpropagation in Deep Neural Networks

Following the introductory section, we have seen that backpropagation is a procedure that involves the repetitive application of the chain rule. Let us now treat its…

Data Science 360

What are the disciplines that we need to cross fertilize to get a system that possesses intelligence?

Deep Neural Networks

DNNs are the implementation of connectionism, the philosophy that calls for algorithms that perform function approximations to be constructed by an interconnection of…

Fashion MNIST Case Study

This is a case study on MNIST Fashion dataset that due to the almost perfect classification of MNIST is now the new point of reference dataset to learn and try ML algorithms…

Introduction to Deep Learning

There are two main benefits that Deep Neural Networks (DNNs) brought to the table, on top of their superior performance in large datasets that we will see later.

Detectron2 Beginner’s Tutorial

Welcome to detectron2! This is the official colab tutorial of detectron2. Here, we will go through some basics usage of detectron2, including the following: * Run inference…

Introduction to Scene Understanding

In the previous chapters we have treated the perception subsystem mainly from starting the first principles that govern supervised learning to the deep learning…

Mask R-CNN - Inspect Trained Model

Code and visualizations to test, debug, and evaluate the Mask R-CNN model.

Mask R-CNN - Inspect Training Data

Inspect and visualize data loading and pre-processing code.

Mask R-CNN - Inspect Weights of a Trained Model

This notebook includes code and visualizations to test, debug, and evaluate the Mask R-CNN model.

Mask R-CNN Demo

A quick intro to using the pre-trained model to detect and segment objects.

Mask R-CNN Semantic Segmentation

The semantic segmentation approach described in this section is Mask R-CNN based on this paper paper. Mask R-CNN is an extension of Faster R-CNN that adds a mask head to the…

Mask R-CNN: A detailed guide with Detectron2:

Welcome to the Mask R-CNN with Detectron2 tutorial!

Object Detection & Semantic Segmentation Workshop

Attention in RNN-based NMT

When you hear the sentence “the soccer ball is on the field,” you don’t assign the same importance to all 7 words. You primarily take note of the words “ball” “on,” and “field…

CNN Language Model

The following was developed by Harini Appansrinivasan, NYU as part of an assignment submission.

Character-level recurrent sequence-to-sequence model

Author: fchollet
Date created: 2017/09/29
Last modified: 2020/04/26
Description: Character-level recurrent sequence-to-sequence model.

Finetuning Language Models for Text Classification - Patent Dataset

This notebook was submitted by NYU student Sky Achitoff

Pantelis Monogioudis

Introduction to NLP Pipelines

In this chapter, we will introduce the topic of processing with neural architectures language in general. This includes natural language, code etc.

LSTM Language Model from scratch

This notebook was borrowed from Christina Kouridis’ github. The notation is different than the notation used in the LTSM section of the notes and will be changed in a next…

Language Models

These notes heavily borrowing from the CS224N set of notes on Language Models.

Language Models Workshop

The following notebook is a from-scratch attempt on character-level language modeling. Its instructive for you to go through it first and then go through the corresponding…

Multi-head self-attention

Earlier we have seen examples with the token bear being in multiple grammatical patterns that also influence its meaning. To capture such multiplicity we can use multiple…

Automated Reasoning

We have seen in an earlier chapter where we introduced a dynamical system governing the state evolution of the environment that a state is composed of variables and such fact…

Logical Agents

In this chapter we see how agents equipped with the ability to represent internally the state of the environment and reason about the effectiveness of possible actions using…

Logical Inference

The wumpus world despite its triviality, contains some deeper abstractions that are worth summarizing.

World Models

For each problem we can define a number of world models each representing every possible state (configuration) of the environment that the agent may be in.

Automated Planning

Planning combines two major areas of AI: logic and search.

Forward Search Algorithms

If you are missing some algorithmic background, afraid not. There is a free and excellent book to help you with the background behind this chapter. Read Chapters 3 and 4 for…

Interactive Demo

This demo is instructive of the various search algorithms we will cover here. You can introduce using your mouse obstacles in the canvas and see how the various search…

Logistics Planning in PDDL

We will use the Logistics domain to illustrate how to represent a planning task in PDDL.

Manufacrturing Robot Planning in PDDL

This is a real case that we tackled for a manufacturing company. This company devises supply chains to make pieces of medical equipments. A supply chain consists of…

Planning Domain Definition Language (PDDL)

In the chapter of propositional logic we have seen the combinatorial explosion problem that results from the need to include in the reasoning / inference step all possible…

Planning with Search

In the PDDL section we saw that a sequence of actions that the agent needs to execute to reach the goal can be obtained using domain-independent planners. This section…

The A* Algorithm

Dijkstra’s algorithm is very much related to the Uniform Cost Search algorithm and in fact logically they are equivalent as the algorithm explores uniformly all nodes that…

The Unified Planning Library

In this demo we will scratch the surface of the UP: we will set it up, we manually create the blocksworld domain using the UP API, we create a problem using a bit of python…

Bellman Expectation Backup

In this section we describe how to calculate the value functions by establishing a recursive relationship similar to the one we did for the return. We replace the…

Bellman Optimality Backup

Now that we can calculate the value functions efficiently via the Bellman expectation recursions, we can now solve the MDP which requires maximize either of the two…

Cleaning Robot - Deterministic MDP

Cleaning Robot - Stochastic MDP

The following code shows the estimation of the q value function for a policy, the optimal q_star and the optimal policy for the cleaning robot problem in the strochastic case.

Finding optimal policies in Gridworld

Introduction to MDP

We start by reviewing the agent-environment interface with this evolved notation and provide additional definitions that will help in grasping the concepts behind DRL. We…

Introduction to MDP

We start by reviewing the agent-environment interface with this evolved notation and provide additional definitions that will help in grasping the concepts behind DRL. We…

Jack’s Car Rental

https://github.com/zy31415/jackscarrental

MDP Dynamic Programming Algorithms

\(\epsilon\)-greedy Monte-Carlo (MC) Control

In this section we outline methods that can result in optimal policies when the MDP is unknown and we need to learn its underlying functions / models - also known as the mode…

Example of \(Q(s,a)\) Prediction

Suppose an agent is learning to play the toy environment shown above. This is a essentially a corridor and the agent has to learn to navigate to the end of the corridor to…

Generalized Policy Iteration

As we saw in the dynamic programming (DP) solution MDP problem, policy iteration is an algorithm that consists of two simultaneous, interacting processes: one making the…

Model-free control

Monte-Carlo Prediction

In this chapter we find optimal policy solutions when the MDP is unknown and we need to learn its underlying value functions - also known as the model free prediction…

Policy Gradient Algorithms - REINFORCE

Given that RL can be posed as an MDP, in this section we continue with a policy-based algorithm that learns the policy directly by optimizing the objective function and can…