Канал: ogsconnect

Chain-of-Thought Reasoning without Prompting

Chain-of-Thought Reasoning without Prompting

#2 Exploratory Analysis on Structured data

#2 Exploratory Analysis on Structured data

#1 Exploratory Analysis on Structured data

#1 Exploratory Analysis on Structured data

Week 3 correction

Week 3 correction

Transformers: Text Classification for NLP using BERT [Jonathan Fernandes]

Transformers: Text Classification for NLP using BERT [Jonathan Fernandes]

L3 - Data Analysis with Python and PySpark

L3 - Data Analysis with Python and PySpark

L2 - Data Analysis with Python and PySpark

L2 - Data Analysis with Python and PySpark

L1 - Data Analysis with Python and PySpark

L1 - Data Analysis with Python and PySpark

PySpark SQL with Examples

PySpark SQL with Examples

Convert PySpark DataFrame to Pandas

Convert PySpark DataFrame to Pandas

Learning Pyspark

Learning Pyspark

208. Implement Trie (Prefix Tree)

208. Implement Trie (Prefix Tree)

802. Find Eventual Safe States

802. Find Eventual Safe States

1219. Path with Maximum Gold

1219. Path with Maximum Gold

1557. Minimum Number of Vertices to Reach All Nodes

1557. Minimum Number of Vertices to Reach All Nodes

Leetcode #1791. Find Center of Star Graph

Leetcode #1791. Find Center of Star Graph

The very first software application I developed way back in 2012!

The very first software application I developed way back in 2012!

L3 : Classify structured data using Keras Preprocessing Layer

L3 : Classify structured data using Keras Preprocessing Layer

L2 : Classify structured data using Keras Preprocessing Layer

L2 : Classify structured data using Keras Preprocessing Layer

Classify structured data using Keras Preprocessing Layer

Classify structured data using Keras Preprocessing Layer

CUDA out of memory error

CUDA out of memory error

pgan for 2 day

pgan for 2 day

#3 Visual Question Answering (VQA) Research [Week 1]

#3 Visual Question Answering (VQA) Research [Week 1]

#2 Visual Question Answering (VQA) Research [Week 1]

#2 Visual Question Answering (VQA) Research [Week 1]

#1 Visual Question Answering (VQA) Research [Week 1]

#1 Visual Question Answering (VQA) Research [Week 1]

Predicting video sequence from reversed input frames

Predicting video sequence from reversed input frames

L6: Anomaly Detection in Computer Vision

L6: Anomaly Detection in Computer Vision

L5 - Anomaly Detection in Computer Vision

L5 - Anomaly Detection in Computer Vision

L4 - Anomaly Detection in Computer Vision

L4 - Anomaly Detection in Computer Vision

L3 - Anomaly Detection in Computer Vision

L3 - Anomaly Detection in Computer Vision

L2 - Anomaly Detection in Computer Vision

L2 - Anomaly Detection in Computer Vision

L1 - Anomaly Detection in Computer Vision

L1 - Anomaly Detection in Computer Vision

Using Autoencoder to replace missing pixel patches in images

Using Autoencoder to replace missing pixel patches in images

Using SKlearn implementation of Random Forest to analyse Udat results of insulators

Using SKlearn implementation of Random Forest to analyse Udat results of insulators

L4 - Computer Science Research

L4 - Computer Science Research

Bias-Variance Tradeoff

Bias-Variance Tradeoff

A review of Machine Learning and Data Science Blueprints for Finance

A review of Machine Learning and Data Science Blueprints for Finance

Creating a shell script for submitting hpc job

Creating a shell script for submitting hpc job

Running experiments on high performance computing cluster

Running experiments on high performance computing cluster

Data Dimension - Volume, Velocity and Variety of data

Data Dimension - Volume, Velocity and Variety of data

Algorithm Design Techniques

Algorithm Design Techniques

L1 - A review of the book 40 Algorithms every programmer should know

L1 - A review of the book 40 Algorithms every programmer should know

L3 - Computer Science Research

L3 - Computer Science Research

L2 - Computer Science Research

L2 - Computer Science Research

L1- Computer Science Research

L1- Computer Science Research

Machine Learning Model Development steps

Machine Learning Model Development steps

A Transformer-based approach for detecting risky tackles in American Football Video

A Transformer-based approach for detecting risky tackles in American Football Video

Next-Frame Football Video prediction

Next-Frame Football Video prediction

Embedding operation - Transformer architecture components

Embedding operation - Transformer architecture components

Add operation - Transformer architecture components

Add operation - Transformer architecture components

SinGAN: Learning a Generative Model from a Single Natural Image

SinGAN: Learning a Generative Model from a Single Natural Image

Siamese Neural Networks for One-shot Image Recognition

Siamese Neural Networks for One-shot Image Recognition

Transferring GANs: generating images from limited data

Transferring GANs: generating images from limited data

Data2vec: A general framework for self-supervised learning in speech, vision and language

Data2vec: A general framework for self-supervised learning in speech, vision and language

Paper reading: Goal-Oriented Gaze Estimation for Zero-Shot Learning

Paper reading: Goal-Oriented Gaze Estimation for Zero-Shot Learning

Transformer-based approach to detecting safe and risky tackles in sport video analytics.

Transformer-based approach to detecting safe and risky tackles in sport video analytics.

Generalization vs Optimization in machine learning

Generalization vs Optimization in machine learning

973. K Closest Points to Origin

973. K Closest Points to Origin

111. Minimum Depth of Binary Tree

111. Minimum Depth of Binary Tree

1431. Kids With the Greatest Number of Candies

1431. Kids With the Greatest Number of Candies

1470. Shuffle the Array

1470. Shuffle the Array

73. Set Matrix Zeroes

73. Set Matrix Zeroes

383. Ransom Note

383. Ransom Note

692. Top K Frequent Words

692. Top K Frequent Words

451. Sort Characters By Frequency

451. Sort Characters By Frequency

1512. Number of Good Pairs

1512. Number of Good Pairs

2011. Final Value of Variable After Performing Operations

2011. Final Value of Variable After Performing Operations

Energy Functions in Deep Learning

Energy Functions in Deep Learning

How to rename multiple files using thunar

How to rename multiple files using thunar

Memory error: std::bad_alloc

Memory error: std::bad_alloc

Five essential steps to performing Data Science

Five essential steps to performing Data Science

Using mmv to rename multiple files

Using mmv to rename multiple files

771. Jewels and Stones

771. Jewels and Stones

205. Isomorphic Strings

205. Isomorphic Strings

21. Merge Two Sorted Lists

21. Merge Two Sorted Lists

2. Add Two Numbers

2. Add Two Numbers

237. Delete Node in a Linked List

237. Delete Node in a Linked List

226. Invert Binary Tree

226. Invert Binary Tree

4. Median of Two Sorted Arrays

4. Median of Two Sorted Arrays

938. Range Sum of BST

938. Range Sum of BST

876. Middle of the Linked List

876. Middle of the Linked List

1290. Convert Binary Number in a Linked List to Integer

1290. Convert Binary Number in a Linked List to Integer

515. Find Largest Value in Each Tree Row

515. Find Largest Value in Each Tree Row

104. Maximum Depth of Binary Tree

104. Maximum Depth of Binary Tree

1365. How Many Numbers Are Smaller Than the Current Number

1365. How Many Numbers Are Smaller Than the Current Number

1672. Richest Customer Wealth

1672. Richest Customer Wealth

1480. Running Sum of 1d Array

1480. Running Sum of 1d Array

Binary Tree - L2

Binary Tree - L2

L1 - Binary Trees

L1 - Binary Trees

i.i.d. samples

i.i.d. samples

Underfitting, Overfitting and Generalization

Underfitting, Overfitting and Generalization

Solution to Keras can not load custom Loss functions

Solution to Keras can not load custom Loss functions

eGAN: Unsupervised approach to class imbalance using transfer learning

eGAN: Unsupervised approach to class imbalance using transfer learning

Representation Learning in Deep Learning

Representation Learning in Deep Learning

Skip Connections and Residual block

Skip Connections and Residual block

ModelCheckpoint - Save best network weights while training

ModelCheckpoint - Save best network weights while training

Inception Module

Inception Module

Global Average Pooling

Global Average Pooling

Cross Entropy loss in codes

Cross Entropy loss in codes

Siamese Neural Network training on Bumble Bees

Siamese Neural Network training on Bumble Bees

Setting up virtual environment

Setting up virtual environment

How to submit batch job to Beocat - L2

How to submit batch job to Beocat - L2

Setting up Virtual Environment on Beocat

Setting up Virtual Environment on Beocat

Calculating loss values - L6

Calculating loss values - L6

Implementing feedforward propagation - L5

Implementing feedforward propagation - L5

A Neuron - L4

A Neuron - L4

Building blocks of ANN - L3

Building blocks of ANN - L3

Comparing AI and traditional machine learning - L2

Comparing AI and traditional machine learning - L2

Artificial Neural Network Fundamentals - L1

Artificial Neural Network Fundamentals - L1

Training loss and Error metrics - L6

Training loss and Error metrics - L6

Optimizer, Gradient Descent - L5

Optimizer, Gradient Descent - L5

Probability, Odd, Logits, Sigmoid, Softmax - L3

Probability, Odd, Logits, Sigmoid, Softmax - L3

Activation Functions - L4

Activation Functions - L4

What is a Tensor - L2

What is a Tensor - L2

Practical Machine Learning for Computer Vision - L1

Practical Machine Learning for Computer Vision - L1

AdeNet presentation at Newark, New Jersey

AdeNet presentation at Newark, New Jersey

generated bee images v2

generated bee images v2

generated bee images

generated bee images

Photo-Realistic Single Image Super-Resolution Using a Generative AdversarialNetwork

Photo-Realistic Single Image Super-Resolution Using a Generative AdversarialNetwork

Using SRGANs to Generate Photo-Realistic Images

Using SRGANs to Generate Photo-Realistic Images

Chapter 2: Lecture 3

Chapter 2: Lecture 3

Chapter 2: Performing Image Classification

Chapter 2: Performing Image Classification

Chapter 2: Performing Image Classification

Chapter 2: Performing Image Classification

Chapter 1: Lecture 3

Chapter 1: Lecture 3

Chapter 1: Lecture 2

Chapter 1: Lecture 2

Chapter 1: Getting Started with TensorFlow 2.x for Computer Vision

Chapter 1: Getting Started with TensorFlow 2.x for Computer Vision

TensorFlow 2.0 Computer Vision Cookbook

TensorFlow 2.0 Computer Vision Cookbook

Anomaly Detection in Computer Vision using Deep Learning

Anomaly Detection in Computer Vision using Deep Learning

addressing imbalance with autokeras

addressing imbalance with autokeras

tackle sport study captioning

tackle sport study captioning

Visualizing pretrained GAN with epochs

Visualizing pretrained GAN with epochs

Encoder DCGAN anomaly detection in video frames 8

Encoder DCGAN anomaly detection in video frames 8

Encoder DCGAN anomaly detection in video frames 7

Encoder DCGAN anomaly detection in video frames 7

Encoder DCGAN anomaly detection in video frames 6

Encoder DCGAN anomaly detection in video frames 6

Encoder DCGAN anomaly detection in video frames 3

Encoder DCGAN anomaly detection in video frames 3

Encoder DCGAN anomaly detection in video frames 2

Encoder DCGAN anomaly detection in video frames 2

Encoder DCGAN anomaly detection in video frames

Encoder DCGAN anomaly detection in video frames

autoencoder with cropped videos for anomaly detection

autoencoder with cropped videos for anomaly detection

GAN Ensemble for Anomaly Detection

GAN Ensemble for Anomaly Detection

object detection bumble bee inferencing

object detection bumble bee inferencing

tensorflow object detection bumble bee

tensorflow object detection bumble bee

clustering images by underlying distribution

clustering images by underlying distribution

Efficient GAN Anomaly Detection

Efficient GAN Anomaly Detection

SinGAN on tackle video

SinGAN on tackle video

Using UPPAAL real-time system to estimate constraints for Convolutional Neural Networks

Using UPPAAL real-time system to estimate constraints for Convolutional Neural Networks

How to upload images from directory in TensorFlow and convert BatchDataset to Numpy array.

How to upload images from directory in TensorFlow and convert BatchDataset to Numpy array.

492

492

493

493

convolutional autoencoder

convolutional autoencoder

learning on abnormal data points

learning on abnormal data points

preparing and running frame level anomalies experiment

preparing and running frame level anomalies experiment

frame level anomalies in videos

frame level anomalies in videos

sport tackle result

sport tackle result

Frame level anomalies in videos training

Frame level anomalies in videos training

UCSD Anomaly Detection pedestrian 1

UCSD Anomaly Detection pedestrian 1

Defining Local Variables using Let construct in SML

Defining Local Variables using Let construct in SML

PyTorch size mismatch RuntimeError

PyTorch size mismatch RuntimeError

PyTorch pin memory RuntimeError

PyTorch pin memory RuntimeError

deepMil PyTorch training

deepMil PyTorch training

DeepMIL Pytorch Version - Anomaly Detection in Surveillance Videos

DeepMIL Pytorch Version - Anomaly Detection in Surveillance Videos

C3D feature extraction in Pytorch

C3D feature extraction in Pytorch

1 minute video NeurIPS BAI

1 minute video NeurIPS BAI

tackle study sport video classification using LSTM inferencing

tackle study sport video classification using LSTM inferencing

tackle study sport video classification using c3d

tackle study sport video classification using c3d

tackle study sport video classification using conv_3d

tackle study sport video classification using conv_3d

tackle study sport video classification using mlp

tackle study sport video classification using mlp

tackle study sport video classification using lstm

tackle study sport video classification using lstm

tackle study sport video classification

tackle study sport video classification

Video Classification training and inferencing

Video Classification training and inferencing

Software Design, Model - L2

Software Design, Model - L2

Video Classification

Video Classification

Software Design, Software, Products - L1

Software Design, Software, Products - L1

Data augmentation in TensorFlow Functional API

Data augmentation in TensorFlow Functional API

Walkthrough of Lab9 - ELK stack basics

Walkthrough of Lab9 - ELK stack basics

Short Presentation on my PhD Research Thesis

Short Presentation on my PhD Research Thesis

variable sized images CNN

variable sized images CNN

Statistical Learning approach to Image Classification - 4

Statistical Learning approach to Image Classification - 4

Statistical Learning approach to Image Classification - 2

Statistical Learning approach to Image Classification - 2

Statistical Learning approach to Image Classification - 3

Statistical Learning approach to Image Classification - 3

Statistical Learning approach to Image Classification - 1

Statistical Learning approach to Image Classification - 1

Lab5 - Pyspark

Lab5 - Pyspark

Evaluating, Training and Converting RetinaNet Model

Evaluating, Training and Converting RetinaNet Model

Weka result with Multilayer perceptron - 81% accuracy

Weka result with Multilayer perceptron - 81% accuracy

Weka result - 85% classification accuracy using RandomForest classifier

Weka result - 85% classification accuracy using RandomForest classifier

Dedamage using Autoencoder

Dedamage using Autoencoder

LeetCode 240. Search a 2D Matrix II

LeetCode 240. Search a 2D Matrix II

Leetcode 867. Transpose Matrix

Leetcode 867. Transpose Matrix

Using Weka to Analyse the exported csv file from Udat Software

Using Weka to Analyse the exported csv file from Udat Software

LeetCode - 130. Surrounded Regions

LeetCode - 130. Surrounded Regions

object detection analysis

object detection analysis

Analyzing udat csv output

Analyzing udat csv output

Udat Result on Beocat

Udat Result on Beocat

Running Udat software on beocat

Running Udat software on beocat

skipganomaly

skipganomaly

classifying insulator with ResNet101

classifying insulator with ResNet101

PGAN Synthesized with small number of images

PGAN Synthesized with small number of images

SinGAN: Learning a Generative Model from a Single Natural Image

SinGAN: Learning a Generative Model from a Single Natural Image

Image classification result with Udat v2

Image classification result with Udat v2

insulator image classification

insulator image classification

Insulator classification with Udat software

Insulator classification with Udat software