MNIST Archives - EITCA Academy

In the example keras.layer.Dense(128, activation=tf.nn.relu) is it possible that we overfit the model if we use the number 784 (28*28)?

Tuesday, 07 October 2025 by ASAD BAIG

The question concerns the use of the `Dense` layer in a neural network model built using Keras and TensorFlow, specifically relating to the number of units chosen for the layer and its implications on model overfitting, with reference to the input dimensionality of 28×28, which totals 784 features (commonly representing flattened grayscale images from datasets

Published in Artificial Intelligence, EITC/AI/TFF TensorFlow Fundamentals, Introduction to TensorFlow, Basic computer vision with ML

Tagged under: Artificial Intelligence, Computer Vision, Keras, MNIST, Model Capacity, Neural Networks, Overfitting, TensorFlow

We care about your privacy

EITCI uses cookies and similar technologies to keep this site secure, remember your choices, provide personalized experience, measure the traffic, serve more relevant content and certification programmes. You can accept all cookies or customize your preferences. Cookies are variables used to store website specific information on your device to facilitate processing of data for personalized website visit, such as login to your account, accessing the programmes, placing enrolment orders in chosen programmes and improving your EITC certification journey. You can change or withdraw your consent at any time by clicking the Consent Preferences button at the left-bottom of your screen. We respect your choices and are committed to providing you with a transparent and secure browsing experience, which may be limited when cookies aren't accepted. For more details refer to the Privacy Policy

EITCA Academy

In the example keras.layer.Dense(128, activation=tf.nn.relu) is it possible that we overfit the model if we use the number 784 (28*28)?

EITCA Academy is a part of the European IT Certification framework

We care about your privacy

Necessary

Functional

Preferences

External media and social features

Analytics

Marketing and conversions

EITCA Academy

LOG IN TO YOUR ACCOUNT

FORGOT YOUR PASSWORD?

CREATE AN ACCOUNT

In the example keras.layer.Dense(128, activation=tf.nn.relu) is it possible that we overfit the model if we use the number 784 (28*28)?

We care about your privacy