Post

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @Sachintukumar

Sachin Kumar

@Sachintukumar

Mar 27, 2024

📝Day 35 of #Deeplearning

✅Topic - Backpropagation in CNN

▫️ #BackPropagation is an algorithm to train neural networks. It is the method of fine-tuning weights of a neural network based on error rate obtained in previous epoch (i.e., iteration)

A Complete 🧵

✅Backpropagation is an algorithm for supervised learning of artificial neural networks using #gradientdescent

Given an artificial neural network and an error function, method calculates gradient of error function with respect to neural network's weights using chain rule

▫️ Total Trainable Parameters-

▫️ Forward Propagation-

Read 13 tweets

Sachin Kumar

@Sachintukumar

Mar 24, 2024

✅Day 32 of #Deeplearning

📝Topic - Padding & Strides

▫️ #Padding is simply a process of adding layers of zeros to our input images

▫️ #Stride describes step size of kernel when you slide a filter over an input image

A Complete 🧵

▫️ Padding is simply a process of adding layers of zeros to our input images.

The purpose of padding is to preserve original size of an image when applying a #convolutional filter & enable filter to perform full convolutions on edge pixel

▫️ So to prevent this-

We will be using padding of size 2 (i.e. original image(5) – feature map(3)).

It is also known as zero padding because we are padding it with 0

Read 13 tweets

Sachin Kumar

@Sachintukumar

Mar 20, 2024

✅Day 29 of #Deeplearning

▫️ Topic - Keras Tuner & Hyperparameter Tuning

📝#KerasTuner is a powerful library that allows you to automate hyperparameter tuning process & search for best model configuration

A Complete 🧵

A ML model has two types of parameters:

Trainable parameters - learned by algorithm during training. For instance weights of a neural network are trainable parameters

#Hyperparameters - set before launching learning process. learning rate in a dense layer are hyperparameter

✅Defining the Model

Define a simple deep learning model that consists of three hidden layers & an output layer with a #softmax activation function

use Adam optimizer and categorical cross-entropy loss function

Read 12 tweets

Sachin Kumar

@Sachintukumar

Feb 17, 2024

✅Day6⃣ of #Deeplearning🧬

▫️ Topic - Multilayer Perceptrons

📝#Multilayerperceptron is type of feedforward neural network consisting of fully connected neurons with nonlinear kind of activation function

It is widely used to distinguish data that is not linearly separable

✅Some of its key concepts

Input layer
Hidden layer
Output layer
Weights
Bias Neurons

✅How Stochastic #GradientDescent (SGD) Work -

Initialization
Iterative Optimization
Direction of Descent
Learning Rate
Convergence

Read 10 tweets

Sachin Kumar

@Sachintukumar

Feb 7, 2024

✅Day1⃣ of #DeepLearning

▫️Topic - Machine Learning (ML) vs Deep Learning (DL)

📝Deep learning is a sub-category of #Machinelearning focused on structuring a learning process for computers where they can recognize patterns & make decisions, much like humans do

A Complete 🧵

DL is essentially a type of sophisticated, multi-layered filter

input raw, unorganized data at top, & it traverses through various layers of neural network, getting refined & analyzed at each level. Eventually, what emerges at bottom is a coherent, structured piece of info a

Input layer -This input can be pixels of an image or a range of time series data

Hidden layer - Commonly known as weights, which are learned while neural network is trained

Output layer - The final layer gives you a prediction of input you fed into your network

Read 8 tweets

Sachin Kumar

@Sachintukumar

Feb 3, 2024

✅Day 95 of #MachineLearning

▫️ Topic - XGBoost Algorithm in Machine Learning🎰

📝#XGBoost efficient handling of missing values is one of its core advantages, allowing it to handle real-world #data with missing values without considerable pre-processing

A Complete Thread🧵

- Optimization & Improvement

process by which ML #algorithm is tuned to improve its performance.This includes adjusting parameters such as learning rate, tree depth, & regularization strength to achieve best model for a given data set

✅XGBoost for Regression

▫️ most commonly #hyperparameters

n_estimators
max_depth
eta
subsample
colsample_bytree

Blog -
machinelearningmastery.com/extreme-gradie…

Read 13 tweets

Share this page!

Enter URL or ID to Unroll

Sachin Kumar

Try unrolling a thread yourself!

More from @Sachintukumar

Sachin Kumar

Sachin Kumar

Sachin Kumar

Sachin Kumar

Sachin Kumar

Sachin Kumar

Did Thread Reader help you today?

Don't want to be a Premium member but still want to support us?

Send Email!