DiaryFolio

  Key Dates of SPY500 During the GFC Event Approximate Date Details 🟩 Initial Peak 2007-10-09 S&P 500 reached 1,565.15 — all-time high before the GFC. 🟥 Bear Market Begins Late Oct 2007 Slow decline started post-peak. 🟨 Bear Market Confirmation 2008-01-09 to 2008-03-17 ~20% drop from peak by March 2008. March 17, 2008 = Bear Stearns bailout . 🟨 Short-term Bottom 2008-03-17 Low of ~1,256 before minor rebound. 🟩 Bear Market Rally / 2nd Peak 2008-05-19 to 2008-06-05 S&P 500 rallied to ~1,428, failed to recover full highs. 🟥 Major Leg Down Begins 2008-09-15 Lehman Brothers collapsed . Market plunged rapidly. 🟥 Panic Selling Bottom 2008-11-20 S&P 500 hit ~ 752 , down ~52% from Oct 2007 peak. 🟨 Bear Rally / Relief Rally 2008-12-08 to 2009-01-06 Short-term bounce to ~935. 🟥 Final Leg Down 2009-01-06 to 2009-03-09 Continued decline to new low. 🟩 GFC Bottom 2009-03-09 Lowest close: 676.53 . Start of long-term recovery. 🕰 Breakdown by Phases: Phase Start Date End Da...

Property Sale: Leveraging the 15-Year Exemption BobCo, a limited company wholly owned by Bob, originally bought a property for $1 million using $50,000 of its own capital and a $950,000 mortgage. By the time Bob sells BobCo (via a share sale), the mortgage is fully paid off, and the property is now worth $2 million. In this post, we’ll explore how this impacts the disposal—specifically Bob’s sale of BobCo’s shares—and the tax implications, including the potential use of the   small business 15-year exemption   to avoid Capital Gains Tax (CGT). Buckle up—this gets intricate! Key Details Initial Purchase Property Cost:   $1 million BobCo’s Capital Contribution:   $50,000 Mortgage:   $950,000 (fully paid off by the time of sale) Sale Context Property Value at Sale:   $2 million Share Sale:   Bob sells 100% of BobCo’s shares to a buyer for $2 million (reflecting the property’s value, assuming no other assets or liabilities) Mortgage Status:   Paid off...

Pre-training and fine-tuning are integral strategies in the development of deep learning models, particularly in the context of transfer learning. In this section, we'll explore these concepts in detail, elucidating how training works and how models are created through these processes. Strategy & Development Pre-training Definition : Pre-training involves training a neural network model on a large dataset to learn generic representations of data features, typically using unsupervised or self-supervised learning techniques. Training Process : During pre-training, the model learns to capture general patterns and features present in the data without being task-specific. This is achieved by optimizing parameters to minimize a predefined loss function, such as reconstruction loss in autoencoders or language modeling loss in transformers. Model Creation: After pre-training, the model's weights and parameters encode valuable knowledge about the underlying data distribution, formi...

Deep learning models come in various architectures and configurations, each tailored to address specific tasks and challenges across different domains. In this section, we'll explore the spectrum of deep learning models, highlighting their types, characteristics, and illustrative examples. 1. Convolutional Neural Networks (CNNs): Characteristics : CNNs excel in tasks involving image recognition, object detection, and computer vision. They leverage convolutional layers to extract spatial features hierarchically from input images, enabling robust and efficient pattern recognition. Examples : AlexNet, VGGNet, ResNet, and MobileNet are popular CNN architectures used for tasks such as image classification, object detection, and semantic segmentation. 2. Recurrent Neural Networks (RNNs): Characteristics : RNNs are well-suited for sequential data processing tasks, including natural language processing, time series analysis, and speech recognition. They maintain internal state (memory) to ...

Transformers have emerged as a revolutionary class of deep learning models, fundamentally reshaping the landscape of natural language processing (NLP). In this comprehensive section, we'll delve into the intricacies of transformers, exploring their architecture, mechanisms, and groundbreaking applications across various NLP tasks. Understanding Transformers: Transformers represent a paradigm shift in NLP, departing from traditional recurrent neural networks (RNNs) and convolutional neural networks (CNNs). Introduced in the seminal paper " Attention is All You Need " by Vaswani et al., transformers leverage self-attention mechanisms to capture long-range dependencies in sequential data efficiently. This architecture enables transformers to process entire sequences of tokens in parallel, circumventing the limitations of sequential processing in RNNs and CNNs. Key Components of Transformers: Self-Attention Mechanism: At the heart of transformers lies the self-attention mecha...

Quantization is a powerful technique used in deep learning to reduce the memory and computational requirements of neural networks by representing weights and activations with fewer bits. In this section, we'll delve into the concept of quantization, elucidating its significance and showcasing its application through examples and diagrams. Understanding Quantization: Quantization involves approximating the floating-point parameters of a neural network with fixed-point or integer representations. By reducing the precision of these parameters, quantization enables the compression of model size and accelerates inference speed, making deep learning models more efficient and deployable on resource-constrained devices. The Process of Quantization: The quantization process typically consists of two main steps: Weight Quantization : In weight quantization, the floating-point weights of the neural network are converted into fixed-point or integer representations with reduced precision. This ...

Tensors are the backbone of modern deep learning, serving as the fundamental data structure for representing and manipulating multi-dimensional data. In this section, we'll explore tensors in greater detail, unraveling their intricate properties and showcasing their versatility through examples. Understanding Tensors: At its core, a tensor is a mathematical object that generalizes scalars, vectors, and matrices to higher dimensions. While  scalars are zero-dimensional (0D) tensors,  vectors are one-dimensional (1D) tensors,  matrices are two-dimensional (2D) tensors.  Tensors extend this concept further, allowing us to represent and manipulate data in three or more dimensions.  This abstraction makes tensors well-suited for capturing the complex relationships present in real-world data, such as images, audio signals, and text. Multiple Dimensions: One of the defining features of tensors is their ability to encapsulate information across multiple dimensions. Cons...