Concept

TensorFlow

Related lectures (22)

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

PyTorch and Convolutional Networks

Covers PyTorch tensor data structure and training a CNN to classify images.

Document Segmentation: dhSegment

Explores the development and improvements of dhSegment, an open-source document segmentation package using PyTorch.

Regression: High Dimensions

Explores linear regression in high dimensions and practical house price prediction from a dataset.

Deep Learning: Convolutional Networks

Explores convolutional neural networks, backpropagation, and stochastic gradient descent in deep learning.

Deep Learning Building Blocks

Covers tensors, loss functions, autograd, and convolutional layers in deep learning.

Neural Networks: Training and Optimization

Explores the training and optimization of neural networks, addressing challenges like non-convex loss functions and local minima.

Deep Learning Fundamentals

Introduces deep learning, from logistic regression to neural networks, emphasizing the need for handling non-linearly separable data.

Quantum Computation: Mechanisms and Advantages of Restricted Models

Covers the mechanisms behind quantum computation and explores the advantages of restricted computational models.

Neural Networks: Two Layers Neural Network

Covers the basics of neural networks, focusing on the development from two layers neural networks to deep neural networks.

Computational Quantum Physics

Covers numerical solutions to Schrödinger equations, quantum Monte Carlo simulations, tensor networks, quantum algorithms, and machine-learning approaches.

Model Finetuning for NLI

Covers the second assignment for the CS-552: Modern NLP course, focusing on transfer learning and data augmentation.

Image Processing

Covers a generic framework for historical document processing using TensorFlow and Python3.

GPUs: Multithreading and Architecture

Explores GPUs' architecture, multithreading, and their role in machine learning, discussing limitations and future trends.

Cross-Validation: Techniques and Applications

Explores cross-validation, overfitting, regularization, and regression techniques in machine learning.

Software: Types and Applications

Explores software types (desktop, mobile, web), open source vs. proprietary software, and key examples like TensorFlow and Red Hat Ansible.

Untitled

Deep Learning: Recurrent Neural Networks

Explores Recurrent Neural Networks for behavioral data, covering Deep Knowledge Tracing, LSTM, GRU networks, hyperparameter tuning, and time series prediction tasks.

Feature Selection, Kernel Regression, Neural Networks Playground

Covers feature selection, kernel regression, and neural networks through exercises.

Variational Method in Relativistic Quantum Field Theory

Delves into the variational method in relativistic quantum field theory without cutoff, emphasizing weakly entangled states and the transition to relativistic continuous matrix product states.